Дисертації: "Outdoor vision and weather"

1

CROCI, ALBERTO. "A novel approach to rainfall measuring: methodology, field test and business opportunity." Doctoral thesis, Politecnico di Torino, 2017. http://hdl.handle.net/11583/2677708.

Повний текст джерела

Анотація:

Being able to measure rainfall is crucial in everyday life. The more rainfall measures are accurate, spatially distributed and detailed in time, the more forecast models - be they meteorological or hydrological - can be accurate. Safety on travel networks could be increased by informing users about the nearby roads’ conditions in real time. In the agricultural sector, being able to gain a detailed knowledge of rainfalls would allow for an optimal management of irrigation, nutrients and phytosanitary treatments. In the sport sector, a better measurement of rainfalls for outdoor events (e.g., motor, motorcycle or bike races) would increase athletes’ safety. Rain gauges are the most common and widely used tools for rainfall measurement. However, the existent monitoring networks still fail in providing accurate spatial representations of localized precipitation events due to the sparseness. This effect is magnified by the intrinsic nature of intense precipitation events, as they are naturally characterized by a great spatial and temporal variability. Potentially, coupling at-ground measures (i.e., coming from pluviometric and disdrometric networks) with remote measurement (e.g., radars or meteorological satellites) could allow to describe the rainfall phenomena in a more continuous and spatially detailed way. However, this kind of approach requires that at-ground measurements are used to calibrate the remote sensors relationships, which leads us back to the dearth of ground networks diffusion. Hence the need to increase the presence of ground measures, in order to gain a better description of the events, and to make a more productive use of the remote sensing technologies. The ambitious aim of the methodology developed in this thesis is to repurpose other sensors already available at ground (e.g., surveillance cameras, webcams, smartphones, cars, etc.) into new source of rain rate measures widely distributed over space and time. The technology, developed to function in daylight conditions, requires that the pictures collected during rainfall events are analyzed to identify and characterize each raindrop. The process leads to an instant measurement of the rain rate associated with the captured image. To improve the robustness of the measurement, we propose to elaborate a higher number of images within a predefined time span (i.e., 12 or more pictures per minute) and to provide an averaged measure over the observed time interval. A schematic summary of how the method works for each acquired image is represented hereinafter : 1. background removal; 2. identification of the rain drops; 3. positioning of each drop in the control volume, by using the blur effect; 4. estimation of drops’ diameters, under the hypothesis that each drop falls at its terminal velocity; 5. rain rate estimation, as the sum of the contributions of each drop. Different techniques for background recognition, drops detection and selection and noise reduction were investigated. Each solution has been applied to the same images sample, in order to identify the combination producing accuracy in the rainfall estimate. The best performing procedure was then validated, by applying it to a wider sample of images. Such a sample was acquired by an experimental station installed on the roof of the Laboratory of Hydraulics of the Politecnico di Torino. The sample includes rainfall events which took place between May 15th, 2016 and February 15th, 2017. Seasonal variability allowed to record events characterized by different intensity in varied light conditions. Moreover, the technology developed during this program of research was patented (2015) and represents the heart of WaterView, spinoff of the Politecnico di Torino founded in February 2015, which is currently in charge of the further development of this technology, its dissemination, and its commercial exploitation.

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Asmar, Daniel. "Vision-Inertial SLAM using Natural Features in Outdoor Environments." Thesis, University of Waterloo, 2006. http://hdl.handle.net/10012/2843.

Повний текст джерела

Анотація:

Simultaneous Localization and Mapping (SLAM) is a recursive probabilistic inferencing process used for robot navigation when Global Positioning Systems (GPS) are unavailable. SLAM operates by building a map of the robot environment, while concurrently localizing the robot within this map. The ultimate goal of SLAM is to operate anywhere using the environment's natural features as landmarks. Such a goal is difficult to achieve for several reasons. Firstly, different environments contain different types of natural features, each exhibiting large variance in its shape and appearance. Secondly, objects look differently from different viewpoints and it is therefore difficult to always recognize them. Thirdly, in most outdoor environments it is not possible to predict the motion of a vehicle using wheel encoders because of errors caused by slippage. Finally, the design of a SLAM system to operate in a large-scale outdoor setting is in itself a challenge.

The above issues are addressed as follows. Firstly, a camera is used to recognize the environmental context (e. g. , indoor office, outdoor park) by analyzing the holistic spectral content of images of the robot's surroundings. A type of feature (e. g. , trees for a park) is then chosen for SLAM that is likely observable in the recognized setting. A novel tree detection system is introduced, which is based on perceptually organizing the content of images into quasi-vertical structures and marking those structures that intersect ground level as tree trunks. Secondly, a new tree recognition system is proposed, which is based on extracting Scale Invariant Feature Transform (SIFT) features on each tree trunk region and matching trees in feature space. Thirdly, dead-reckoning is performed via an Inertial Navigation System (INS), bounded by non-holonomic constraints. INS are insensitive to slippage and varying ground conditions. Finally, the developed Computer Vision and Inertial systems are integrated within the framework of an Extended Kalman Filter into a working Vision-INS SLAM system, named VisSLAM.

VisSLAM is tested on data collected during a real test run in an outdoor unstructured environment. Three test scenarios are proposed, ranging from semi-automatic detection, recognition, and initialization to a fully automated SLAM system. The first two scenarios are used to verify the presented inertial and Computer Vision algorithms in the context of localization, where results indicate accurate vehicle pose estimation for the majority of its journey. The final scenario evaluates the application of the proposed systems for SLAM, where results indicate successful operation for a long portion of the vehicle journey. Although the scope of this thesis is to operate in an outdoor park setting using tree trunks as landmarks, the developed techniques lend themselves to other environments using different natural objects as landmarks.

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Catchpole, Jason James. "Adaptive Vision Based Scene Registration for Outdoor Augmented Reality." The University of Waikato, 2008. http://hdl.handle.net/10289/2581.

Повний текст джерела

Анотація:

Augmented Reality (AR) involves adding virtual content into real scenes. Scenes are viewed using a Head-Mounted Display or other display type. In order to place content into the user's view of a scene, the user's position and orientation relative to the scene, commonly referred to as their pose, must be determined accurately. This allows the objects to be placed in the correct positions and to remain there when the user moves or the scene changes. It is achieved by tracking the user in relation to their environment using a variety of technology. One technology which has proven to provide accurate results is computer vision. Computer vision involves a computer analysing images and achieving an understanding of them. This may be locating objects such as faces in the images, or in the case of AR, determining the pose of the user. One of the ultimate goals of AR systems is to be capable of operating under any condition. For example, a computer vision system must be robust under a range of different scene types, and under unpredictable environmental conditions due to variable illumination and weather. The majority of existing literature tests algorithms under the assumption of ideal or 'normal' imaging conditions. To ensure robustness under as many circumstances as possible it is also important to evaluate the systems under adverse conditions. This thesis seeks to analyse the effects that variable illumination has on computer vision algorithms. To enable this analysis, test data is required to isolate weather and illumination effects, without other factors such as changes in viewpoint that would bias the results. A new dataset is presented which also allows controlled viewpoint differences in the presence of weather and illumination changes. This is achieved by capturing video from a camera undergoing a repeatable motion sequence. Ground truth data is stored per frame allowing images from the same position under differing environmental conditions, to be easily extracted from the videos. An in depth analysis of six detection algorithms and five matching techniques demonstrates the impact that non-uniform illumination changes can have on vision algorithms. Specifically, shadows can degrade performance and reduce confidence in the system, decrease reliability, or even completely prevent successful operation. An investigation into approaches to improve performance yields techniques that can help reduce the impact of shadows. A novel algorithm is presented that merges reference data captured at different times, resulting in reference data with minimal shadow effects. This can significantly improve performance and reliability when operating on images containing shadow effects. These advances improve the robustness of computer vision systems and extend the range of conditions in which they can operate. This can increase the usefulness of the algorithms and the AR systems that employ them.

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Ahmed, Maryum F. "Development of a stereo vision system for outdoor mobile robots." [Gainesville, Fla.] : University of Florida, 2006. http://purl.fcla.edu/fcla/etd/UFE0016205.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Lin, Li-Heng. "Enhanced stereo vision SLAM for outdoor heavy machine rotation sensing." Thesis, University of British Columbia, 2010. http://hdl.handle.net/2429/25966.

Повний текст джерела

Анотація:

The thesis presents an enhanced stereo vision Simultaneous Localization and Mapping (SLAM) algorithm that permits reliable camera pose estimation in the presence of directional sunlight illumination causing shadows and non-uniform scene lighting. The algorithm has been developed to measure a mining rope shovel's rotation angle about its vertical axis ("swing" axis). A stereo camera is mounted externally to the shovel house (upper revolvable portion of the shovel), with a clear view of the shovel's lower carbody. As the shovel house swings, the camera revolves with the shovel house in a circular orbit, seeing differing views of the carbody top. While the shovel swings, the algorithm records observed 3D features on the carbody as landmarks, and incrementally builds a 3D map of the landmarks as the camera revolves around the carbody. At the same time, the algorithm localizes the camera with respect to this map. The estimated camera position is in turn used to calculate the shovel swing angle. The algorithm enhancements include a "Locally Maximal" Harris corner selection method which allows for more consistent feature selection in the presence of directional sunlight causing shadows and non-uniform scene lighting. Another enhancement is the use of 3D "Feature Cluster" landmarks rather than single feature landmarks, which improves the robustness of the landmark matching and reduces the SLAM filter's computational cost. The vision-based sensor's maximum swing angle error is less than +/- 1 degree upon map convergence. Results demonstrate the improvements of using the novel techniques compared to past methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Alamgir, Nyma. "Computer vision based smoke and fire detection for outdoor environments." Thesis, Queensland University of Technology, 2020. https://eprints.qut.edu.au/201654/1/Nyma_Alamgir_Thesis.pdf.

Повний текст джерела

Анотація:

Surveillance Video-based detection of outdoor smoke and fire has been a challenging task due to the chaotic variations of shapes, movement, colour, texture, and density. This thesis contributes to the advancement of the contemporary efforts of smoke and fire detection by proposing novel technical methods and their possible integration into a complete fire safety model. The novel contributions of this thesis include an efficient feature calculation method combining local and global texture properties, the development of deep learning-based models and a conceptual framework to incorporate weather information in the fire safety model for improved accuracy in fire prediction and detection.

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Williams, Samuel Grant Dawson. "Real-Time Hybrid Tracking for Outdoor Augmented Reality." Thesis, University of Canterbury. Computer Science and Software Engineering, 2014. http://hdl.handle.net/10092/9188.

Повний текст джерела

Анотація:

Outdoor tracking and registration are important enabling technologies for mobile augmented reality. Sensor fusion and image processing can be used to improve global tracking and registration for low-cost mobile devices with limited computational power and sensor accuracy. Prior research has confirmed the benefits of this approach with high-end hardware, however the methods previously used are not ideal for current consumer mobile devices. We discuss the development of a hybrid tracking and registration algorithm that combines multiple sensors and image processing to improve on existing work in both performance and accuracy. As part of this, we developed the Transform Flow toolkit, which is one of the first open source systems for developing and quantifiably evaluating mobile AR tracking algorithms. We used this system to compare our proposed hybrid tracking algorithm with a purely sensor based approach, and to perform a user study to analyse the effects of improved precision on real world tracking tasks. Our results show that our implementation is an improvement over a purely sensor fusion based approach; accuracy is improved up to 25x in some cases with only 2-4ms additional processing per frame, in comparison with other algorithms which can take over 300ms.

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Schreiber, Michael J. "Outdoor tracking using computer vision, xenon strobe illumination and retro-reflective landmarks." Diss., Georgia Institute of Technology, 1996. http://hdl.handle.net/1853/18940.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Rosenquist, Calle, and Andreas Evesson. "Visual Servoing In Semi-Structured Outdoor Environments." Thesis, Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-653.

Повний текст джерела

Анотація:

The field of autonomous vehicle navigation and localization is a highly active research

topic. The aim of this thesis is to evaluate the feasibility to use outdoor visual navigation in a semi-structured environment. The goal is to develop a visual navigation system for an autonomous golf ball collection vehicle operating on driving ranges.

The image feature extractors SIFT and PCA-SIFT was evaluated on an image database

consisting of images acquired from 19 outdoor locations over a period of several weeks to

allow different environmental conditions. The results from these tests show that SIFT-type

feature extractors are able to find and match image features with high accuracy. The results also show that this can be improved further by a combination of a lower nearest neighbour threshold and an outlier rejection method to allow more matches and a higher ratio of correct matches. Outliers were found and rejected by fitting the data to a homography model with the RANSAC robust estimator algorithm.

A simulator was developed to evaluate the suggested system with respect to pixel noise from illumination changes, weather and feature position accuracy as well as the distance to features, path shapes and the visual servoing target image (milestone) interval. The system was evaluated on a total of 3 paths, 40 test combinations and 137km driven. The results show that with the relatively simple visual servoing navigation system it is possible to use mono-vision as a sole sensor and navigate semi-structured outdoor environments such as driving ranges.

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Linegar, Chris. "Vision-only localisation under extreme appearance change." Thesis, University of Oxford, 2016. https://ora.ox.ac.uk/objects/uuid:608762bd-5608-4e50-ab7b-da454dd52887.

Повний текст джерела

Анотація:

Robust localisation is a key requirement for autonomous vehicles. However, in order to achieve widespread adoption of this technology, we also require this function to be performed using low-cost hardware. Cameras are appealing due to their information-rich image content and low cost; however, camera-based localisation is difficult because of the problem of appearance change. For example, in outdoor en- vironments the appearance of the world can change dramatically and unpredictably with variations in lighting, weather, season and scene structure. We require autonomous vehicles to be robust under these challenging environmental conditions. This thesis presents Dub4, a vision-only localisation system for autonomous vehicles. The system is founded on the concept of experiences, where an "experience" is a visual memory which models the world under particular conditions. By allowing the system to build up and curate a map of these experiences, we are able to handle cyclic appearance change (lighting, weather and season) as well as adapt to slow structural change. We present a probabilistic framework for predicting which experiences are most likely to match successfully with the live image at run-time, conditioned on the robot's prior use of the map. In addition, we describe an unsupervised algorithm for detecting and modelling higher-level visual features in the environment for localisation. These features are trained on a per-experience basis and are robust to extreme changes in appearance, for example between rain and sun, or day and night. The system is tested on over 1500km of data, from urban and off-road environments, through sun, rain, snow, harsh lighting, at different times of the day and night, and through all seasons. In addition to this extensive offline testing, Dub4 has served as the primary localisation source on a number of autonomous vehicles, including the Oxford University's RobotCar, the 2016 Shell Eco-Marathon, the LUTZ PathFinder Project in Milton Keynes, and the GATEway Project in Greenwich, London.

Стилі APA, Harvard, Vancouver, ISO та ін.

11

Eriksson, Ida. "Idrottslärares syn på friluftslivsundervisningen i skolan." Thesis, Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-31776.

Повний текст джерела

Анотація:

Friluftsliv täcker en stor del av det centrala innehållet i Lgr11 i ämnet idrott och hälsa. Syftet med undersökningen är att få en bild av idrottslärarnas syn på, och vision med friluftsverksamheten i skolan, hur den egentligen ser ut samt vad lärarna anser behövs för att visionerna ska uppfyllas. Frågeställningarna är därför: Hur uppfattar lärarna att friluftsundervisningen ser ut i skolan idag? Vad är lärarnas vision av friluftsundervisningen? Vad behövs enligt lärarna göras för att visionerna ska uppfyllas? Undersökningen har genomförts genom fyra semistrukturerade intervjuer med idrottslärare som arbetar på högstadiet. Dessa har sedan transkriberats och analyserats. Resultatet av deras uppfattningar visar att friluftsundervisningen i skolan skiljer sig gentemot deras vision. Den friluftsundervisning som finns i skolan idag är oftast kopplat till ett större projekt som t.ex. friluftsdagar vilket resulterar i punktinsatser. Den samlade bilden av lärarnas vision är att minska punktinsatserna och samtidigt ha möjligheten till att ta med eleverna på längre resor där de kan testa på skidåkning, vandring, fiske, tälta m.m. För att lärarnas vision ska kunna uppfyllas menar de att det behövs tid, pengar och material enligt respondenterna, precis som tidigare forskning också visar.
Outdoor education covers a large part of the core content of Lgr11 in physical education. The purpose of the survey is to get a picture of a group of PE teachers' views on, and visions with outdoor education in school. I´m also interested in how, in fact, the reality looks like and what teachers believe is needed to visions will be achieved. Therefore the questions will be: How do outdoor education looks like in school today, according to the teachers? What is the teacher's vision of outdoor education? What´s needed so the vision will be achieved according to the teachers? The survey was conducted by four semi-structured interviews with PE teachers working at high school. These were then transcribed and the result of their beliefs is that outdoor education in school differs from their vision. The outdoor education that is available in schools today is usually linked to a major project such as sports days and it results in point actions. The overall picture of the teachers´ vision is to reduce point actions while still having the ability to take the students on longer trips where they can try to go skiing, hiking, fishing, camping etc. In order for the vision to become reality it requires time, money and materials according to the respondents, as previous research also shows.

Стилі APA, Harvard, Vancouver, ISO та ін.

12

El, Natour Ghina. "Towards 3D reconstruction of outdoor scenes by mmw radar and a vision sensor fusion." Thesis, Clermont-Ferrand 2, 2016. http://www.theses.fr/2016CLF22773/document.

Повний текст джерела

Анотація:

L’objectif de cette thèse est de développer des méthodes permettant la cartographie d’un environnement tridimensionnel de grande dimension en combinant radar panoramique MMW et caméras optiques. Contrairement aux méthodes existantes de fusion de données multi-capteurs, telles que le SLAM, nous souhaitons réaliser un capteur de type RGB-D fournissant directement des mesures de profondeur enrichies par l’apparence (couleur, texture...). Après avoir modélisé géométriquement le système radar/caméra, nous proposons une méthode de calibrage originale utilisant des correspondances de points. Pour obtenir ces correspondances, des cibles permettant une mesure ponctuelle aussi bien par le radar que la caméra ont été conçues. L’approche proposée a été élaborée pour pouvoir être mise en oeuvre dans un environnement libre et par un opérateur non expert. Deuxièmement, une méthode de reconstruction de points tridimensionnels sur la base de correspondances de points radar et image a été développée. Nous montrons par une analyse théorique des incertitudes combinées des deux capteurs et par des résultats expérimentaux, que la méthode proposée est plus précise que la triangulation stéréoscopique classique pour des points éloignés comme on en trouve dans le cas de cartographie d’environnements extérieurs. Enfin, nous proposons une stratégie efficace de mise en correspondance automatique des données caméra et radar. Cette stratégie utilise deux caméras calibrées. Prenant en compte l’hétérogénéité des données radar et caméras, l’algorithme développé commence par segmenter les données radar en régions polygonales. Grâce au calibrage, l’enveloppe de chaque région est projetée dans deux images afin de définir des régions d’intérêt plus restreintes. Ces régions sont alors segmentées à leur tour en régions polygonales générant ainsi une liste restreinte d’appariement candidats. Un critère basé sur l’inter corrélation et la contrainte épipolaire est appliqué pour valider ou rejeter des paires de régions. Tant que ce critère n’est pas vérifié, les régions sont, elles même, subdivisées par segmentation. Ce processus, favorise l’appariement de régions de grande dimension en premier. L’objectif de cette approche est d’obtenir une cartographie sous forme de patchs localement denses. Les méthodes proposées, ont été testées aussi bien sur des données de synthèse que sur des données expérimentales réelles. Les résultats sont encourageants et montrent, à notre sens, la faisabilité de l’utilisation de ces deux capteurs pour la cartographie d’environnements extérieurs de grande échelle
The main goal of this PhD work is to develop 3D mapping methods of large scale environment by combining panoramic radar and cameras. Unlike existing sensor fusion methods, such as SLAM (simultaneous localization and mapping), we want to build a RGB-D sensor which directly provides depth measurement enhanced with texture and color information. After modeling the geometry of the radar/camera system, we propose a novel calibration method using points correspondences. To obtain these points correspondences, we designed special targets allowing accurate point detection by both the radar and the camera. The proposed approach has been developed to be implemented by non-expert operators and in unconstrained environment. Secondly, a 3D reconstruction method is elaborated based on radar data and image point correspondences. A theoretical analysis is done to study the influence of the uncertainty zone of each sensor on the reconstruction method. This theoretical study, together with the experimental results, show that the proposed method outperforms the conventional stereoscopic triangulation for large scale outdoor scenes. Finally, we propose an efficient strategy for automatic data matching. This strategy uses two calibrated cameras. Taking into account the heterogeneity of cameras and radar data, the developed algorithm starts by segmenting the radar data into polygonal regions. The calibration process allows the restriction of the search by defining a region of interest in the pair of images. A similarity criterion based on both cross correlation and epipolar constraint is applied in order to validate or reject region pairs. While the similarity test is not met, the image regions are re-segmented iteratively into polygonal regions, generating thereby a shortlist of candidate matches. This process promotes the matching of large regions first which allows obtaining maps with locally dense patches. The proposed methods were tested on both synthetic and real experimental data. The results are encouraging and prove the feasibility of radar and vision sensor fusion for the 3D mapping of large scale urban environment

Стилі APA, Harvard, Vancouver, ISO та ін.

13

Botero, galeano Diego andres. "Development of algorithms and architectures for driving assistance in adverse weather conditions using FPGAs." Thesis, Toulouse, INSA, 2012. http://www.theses.fr/2012ISAT0062/document.

Повний текст джерела

Анотація:

En raison de l'augmentation du volume et de la complexité des systèmes de transport, de nouveaux systèmes avancés d'assistance à la conduite (ADAS) sont étudiés dans de nombreuses entreprises, laboratoires et universités. Ces systèmes comprennent des algorithmes avec des techniques qui ont été étudiés au cours des dernières décennies, comme la localisation et cartographie simultanées (SLAM), détection d'obstacles, la vision stéréoscopique, etc. Grâce aux progrès de l'électronique, de la robotique et de plusieurs autres domaines, de nouveaux systèmes embarqués sont développés pour garantir la sécurité des utilisateurs de ces systèmes critiques. Pour la plupart de ces systèmes, une faible consommation d'énergie ainsi qu'une taille réduite sont nécessaires. Cela crée la contrainte d'exécuter les algorithmes sur les systèmes embarqués avec des ressources limitées. Dans la plupart des algorithmes, en particulier pour la vision par ordinateur, une grande quantité de données doivent être traitées à des fréquences élevées, ce qui exige des ressources informatiques importantes. Un FPGA satisfait cette exigence, son architecture parallèle combinée à sa faible consommation d'énergie et la souplesse pour les programmer permet de développer et d'exécuter des algorithmes plus efficacement que sur d'autres plateformes de traitement. Les composants virtuels développés dans cette thèse ont été utilisés dans trois différents projets: PICASSO (vision stéréoscopique), COMMROB (détection d'obstacles à partir d'une système multicaméra) et SART (Système d'Aide au Roulage tous Temps)
Due to the increase of traffic volume and complexity of new transport systems, new Advanced Driver Assistance Systems (ADAS) are a subject of research of many companies, laboratories and universities. These systems include algorithms with techniques that have been studied during the last decades like Simultaneous Lo- calization and Mapping (SLAM), obstacle detection, stereo vision, etc. Thanks to the advances in electronics, robotics and other domains, new embedded systems are being developed to guarantee the safety of the users of these critical systems. For most of these systems a low power consumption as well as reduced size is required. It creates the constraint of execute the algorithms in embedded devices with limited resources. In most of algorithms, moreover for computer vision ones, a big amount of data must be processed at high frequencies, this amount of data demands strong computing resources. FPGAs satisfy this requirement; its parallel architecture combined with its low power consumption and exibility allows developing and executing some algorithms more efficiently than any other processing platforms. In this thesis different embedded computer vision architectures intended to be used in ADAS using FPGAs are presented such as: We present the implementation of a distortion correction architecture operating at 100 Hz in two cameras simultaneously. The correction module allows also to rectify two images for implementation of stereo vision. Obstacle detection algorithms based on Inverse Perspective Mapping (IPM) and classiffication based on Color/Texture attributes are presented. The IPM transform is based in the perspective effect of a scene perceived from two different points of view. Moreover results of the detection algorithms from color/texture attributes applied on a multi-cameras system, are fused in an occupancy grid. An accelerator to apply homographies on images, is presented; this accelerator can be used for different applications like the generation of Bird's eye view or Side view. Multispectral vision is studied using both infrared images and color ones. Syn- thetic images are generated from information acquired from visible and infrared sources to provide a visual aid to the driver. Image enhancement specific for infrared images is also implemented and evaluated, based on the Contrast Lim- ited Adaptive Histogram Equalization (CLAHE). An embedded SLAM algorithm is presented with different hardware acceler- ators (point detection, landmark tracking, active search, correlation, matrix operations). All the algorithms were simulated, implemented and verified using as target FPGAs. The validation was done using development kits. A custom board integrating all the presented algorithms is presented. Virtual components developed in this thesis were used in three different projects: PICASSO (stereo vision), COMMROB (obstacle detection from a multi-cameras system) and SART (multispectral vision)

Стилі APA, Harvard, Vancouver, ISO та ін.

14

Shi, Jie. "Obstacle detection using thermal imaging sensors for large passenger airplane." Thesis, Cranfield University, 2012. http://dspace.lib.cranfield.ac.uk/handle/1826/7944.

Повний текст джерела

Анотація:

This thesis addresses the issue of ground collision in poor weather conditions. As bad weather is an adverse factor when airplanes are taxiing, an obstacle detection system based on thermal vision is proposed to enhance the awareness of pilots during taxiing in poor weather conditions. Two infrared cameras are employed to detect the objects and estimate the distance of the obstacle. The distance is computed by stereo vision technology. A warning will be given if the distance is less than the safe distance predefined. To make the system independent, the proposed system is an on-board system which does not rely on airports or other airplanes. The type of obstacle is classified by the temperature of the object. Fuzzy logic is employed in the classification. Obstacles are classified into three main categories: aircraft, vehicle and people. Membership functions are built based on the temperature distribution of obstacles measured at the airport. In order to improve the accuracy of classification, a concept of using position information is proposed. Different types of obstacle are predefined according to different area at the airport. In the classification, obstacles are classified according to the types limited in that area. Due to the limitation of the thermal infrared camera borrowed, images were captured first and then processed offline. Experiments were carried out to evaluate the detecting distance error and the performance of system in poor weather conditions. The classification of obstacle is simulated with real thermal images and pseudo position information at the airport. The results suggest that the stereo vision system developed in this research was able to detect the obstacle and estimate the distance. The classification method classified the obstacles to a certain extent. Therefore, the proposed system can improve safety of aircraft and enhance situational awareness of pilots. The programming language of the system is Python 2.7. Computer graphic library OpenCV 2.3 is used in processing images. MATLAB is used in the simulation of obstacle classification.

Стилі APA, Harvard, Vancouver, ISO та ін.

15

Sadel, Juraj. "Rozpoznání počasí z kamerových snímků/sekvencí." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2021. http://www.nusl.cz/ntk/nusl-442513.

Повний текст джерела

Анотація:

The aim of my master's thesis is to design and then implement suitable weather classification algorithms mainly focused on the detection of precipitation and fog, including parameterization. The first half of my thesis is devoted to a theoretical description of weather and it's impact on transport. Furthermore, the theory of image processing and neural networks and already existing solutions is approached. Subsequently, the used datasets are described. The practical part of thesis is devoted to the design of possible algorithms based on the theoretical part of the thesis. After the design, the individual algorithms are implemented, tested and evaluated. Finally, a comparison of classical methods and neural networks is described.

Стилі APA, Harvard, Vancouver, ISO та ін.

16

Botero-Galeano, Diego. "Development of algorithms and architectures for driving assistance in adverse weather conditions using FPGAs." Phd thesis, INSA de Toulouse, 2012. http://tel.archives-ouvertes.fr/tel-00771869.

Повний текст джерела

Анотація:

En raison de l'augmentation du volume et de la complexité des systèmes de transport, de nouveaux systèmes avancés d'assistance à la conduite (ADAS) sont étudiés dans de nombreuses entreprises, laboratoires et universités. Ces systèmes comprennent des algorithmes avec des techniques qui ont été étudiés au cours des dernières décennies, comme la localisation et cartographie simultanées (SLAM), détection d'obstacles, la vision stéréoscopique, etc. Grâce aux progrès de l'électronique, de la robotique et de plusieurs autres domaines, de nouveaux systèmes embarqués sont développés pour garantir la sécurité des utilisateurs de ces systèmes critiques. Pour la plupart de ces systèmes, une faible consommation d'énergie ainsi qu'une taille réduite sont nécessaires. Cela crée la contrainte d'exécuter les algorithmes sur les systèmes embarqués avec des ressources limitées. Dans la plupart des algorithmes, en particulier pour la vision par ordinateur, une grande quantité de données doivent être traitées à des fréquences élevées, ce qui exige des ressources informatiques importantes. Un FPGA satisfait cette exigence, son architecture parallèle combinée à sa faible consommation d'énergie et la souplesse pour les programmer permet de développer et d'exécuter des algorithmes plus efficacement que sur d'autres plateformes de traitement. Les composants virtuels développés dans cette thèse ont été utilisés dans trois différents projets: PICASSO (vision stéréoscopique), COMMROB (détection d'obstacles à partir d'une système multicaméra) et SART (Système d'Aide au Roulage tous Temps).

Стилі APA, Harvard, Vancouver, ISO та ін.

17

Kakarlapudi, Swarna. "APPLICATION OF IMAGE ANALYSIS TECHNIQUES IN FORWARD LOOKING SYNTHETIC VISION SYSTEM INTEGRITY MONITORS." Ohio University / OhioLINK, 2004. http://www.ohiolink.edu/etd/view.cgi?ohiou1090265512.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

18

Blanco, Myra. "Relationship Between Driver Characteristics, Nighttime Driving Risk Perception, and Visual Performance under Adverse and Clear Weather Conditions and Different Vision Enhancement Systems." Diss., Virginia Tech, 2002. http://hdl.handle.net/10919/27806.

Повний текст джерела

Анотація:

Vehicle crashes remain the leading cause of accidental death and injuries in the United States, claiming tens of thousands of lives and injuring millions of people each year. Many of these crashes occur during nighttime, where a variety of modifiers affect the risk of a crash, primarily through the reduction of object visibility. Furthermore, many of these modifiers also affect the nighttime mobility of older drivers, who avoid driving during the nighttime. Thus, a two-fold need exists for new technologies that enhance night visibility. Two separate studies were completed as part of this research. Study 1 served as a baseline by evaluating visual performance during nighttime driving under clear weather conditions. Visual performance was evaluated in terms of the detection and recognition distances obtained when different vision enhancement systems were used at the Smart Road testing facility. Study 2, also using detection and recognition distances, compared the visual performance of drivers during low visibility conditions (i.e., due to rain) to the risk perception of driving during nighttime under low visibility conditions. These comparisons were made as a function of various vision enhancement systems. The age of the driver and the characteristics of the object presented (e.g., contrast, motion) were variables of interest in both studies. The pivotal contribution of this investigation is the generation of a model describing the relationships between driver characteristics, risk perception, and visual performance in nighttime driving in the context of a variety of standard and prototype vision enhancement systems. Improvement of mobility, especially for older individuals, can be achieved through better understanding of the factors that increase risk perception, identification of systems that improve detection and recognition distances, and consideration of drivers' opinions on possible solutions that improve nighttime driving safety. In addition, this research effort empirically described the night vision enhancement capabilities of 12 different vision enhancement systems during clear and adverse weather environments.
Ph. D.

Стилі APA, Harvard, Vancouver, ISO та ін.

19

Öberg, Johan, and Erik Wiege. "Moisture risks with CLT-panels subjected to outdoor climate during construction : focus on mould and wetting processes." Thesis, KTH, Byggteknik och design, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-231115.

Повний текст джерела

Анотація:

When going through relevant research, moisture safety guidelines and talking to builders, moisture experts and architects it is clear - and not surprising - that water and wood make no easy combination. The experiences from building with cross laminated timber (CLT) differ from building sites and there are good and bad examples building without weather protection. In this study the moisture influence on CLT is analyzed. CLT is a type of massive wood with glued lamellas, increasing usage worldwide as structural elements in buildings. The bulk of the work is performed in the hygrothermal calculation tool WUFI(™). Focus is on the wetting process and the evaluation of mould risk from rain loads during production in Nordic climates. Subsequent drying after built into walls and floors is also evaluated. A vast literature survey is performed in order to compare and select material data for modelling CLT. Following the simulation work, moisture content, mould growth and volumetric distortion are judged both with and without weather protection. Results are also compared to measurement data from field tests. It is found that short building times are crucial, some weather protection is required all year around and early planning and constructing for moisture safety are crucial. The benefits of prefabrication and short building times using CLT should be exploited. If there is a risk of rainfall exceeding 10-20 mm, arrangements to divert rain loads should be undertaken. If the expected rain loads are above 40 mm or if the building time exceeds 2 weeks, a roof cover will be required. At air humidities averaging 80% and yearly rain exceeding 1200 mm, a complete building cover is recommended. A controlled environment may be expensive, but it speeds up production and shortens drying time.
När man går igenom relevant forskning, riktlinjer för fuktsäkerhet och pratar med byggare, fuktexperter och arkitekter är det tydligt - och inte överraskande - att vatten och trä inte är någon enkel kombination. Erfarenheterna från att bygga med korslimmat trä (KL-trä) skiljer sig från byggarbetsplatser och det finns bra och dåliga exempel från byggande utan väderskydd. I denna studie analyseras fuktpåverkan på KL-trä. KL-trä är en typ av massivt trä med limmade lameller, som ökar i användningen över hela världen som strukturella element i byggnader. Huvuddelen av arbetet utförs i det hygrotermiska beräkningsverktyget WUFI (™). Fokus ligger på uppfuktning och utvärdering av mögelrisker från regnbelastning under produktion i nordiskt klimat. Efterföljande torkning efter inbyggnad i väggar och golv utvärderas också. En omfattande litteraturstudie utförs för att jämföra och välja materialdata för modellering av KL-trä. Efter simuleringsarbetet bedöms fuktinnehåll, mögeltillväxt och fuktrörelser både med och utan väderskydd. Resultaten jämförs också med mätdata från fältförsök. Det konstateras att korta byggtider är avgörande, någon form av väderskydd krävs året runt och tidig planering och konstruktion för fuktsäkerhet är avgörande. Fördelarna med prefabricering och korta byggtider med KL-trä bör utnyttjas. Om det finns risk för nederbörd över 10-20 mm bör åtgärder vidtas för att avleda regn. Om de förväntade regnbelastningarna är över 40 mm eller om byggtiden överstiger 2 veckor krävs ett regnskydd. Vid luftfuktigheter på i medeltal 80 % och årligt regn över 1200 mm rekommenderas ett väderskydd runt hela byggnaden. En kontrollerad miljö kan vara dyr, men det påskyndar produktionen och förkortar torkningstiden.

Стилі APA, Harvard, Vancouver, ISO та ін.

20

Velandia, Henry Roncancio. "Object detection and classication in outdoor environments for autonomous passenger vehicle navigation based on Data Fusion of Articial Vision System and LiDAR sensor." Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/18/18149/tde-24072016-152124/.

Повний текст джерела

Анотація:

This research project took part in the SENA project (Autonomous Embedded Navigation System), which was developed at the Mobile Robotics Lab of the Mechatronics Group at the Engineering School of São Carlos, University of São Paulo (EESC - USP) in collaboration with the São Carlos Institute of Physics. Aiming for an autonomous behavior in the prototype vehicle this dissertation focused on deploying some machine learning algorithms to support its perception. These algorithms enabled the vehicle to execute articial-intelligence tasks, such as prediction and memory retrieval for object classication. Even though in autonomous navigation there are several perception, cognition and actuation tasks, this dissertation focused only on perception, which provides the vehicle control system with information about the environment around it. The most basic information to be provided is the existence of objects (obstacles) around the vehicle. In formation about the sort of object it is also provided, i.e., its classication among cars, pedestrians, stakes, the road, as well as the scale of such an object and its position in front of the vehicle. The environmental data was acquired by using a camera and a Velodyne LiDAR. A ceiling analysis of the object detection pipeline was used to simulate the proposed methodology. As a result, this analysis estimated that processing specic regions in the PDF Compressor Pro xii image (i.e., Regions of Interest, or RoIs), where it is more likely to nd an object, would be the best way of improving our recognition system, a process called image normalization. Consequently, experimental results in a data-fusion approach using laser data and images, in which RoIs were found using the LiDAR data, showed that the fusion approach can provide better object detection and classication compared with the use of either camera or LiDAR alone. Deploying a data-fusion classication using RoI method can be executed at 6 Hz and with 100% precision in pedestrians and 92.3% in cars. The fusion also enabled road estimation even when there were shadows and colored road markers in the image. Vision-based classier supported by LiDAR data provided a good solution for multi-scale object detection and even for the non-uniform illumination problem.
Este projeto de pesquisa fez parte do projeto SENA (Sistema Embarcado de Navegação Autônoma), ele foi realizado no Laboratório de Robótica Móvel do Grupo de Mecatrônica da Escola de Engenharia de São Carlos (EESC), em colaboração com o Instituto de Física de São Carlos (IFSC). A grande motivação do projeto SENA é o desenvolvimento de tecnologias assistidas e autônomas que possam atender às necessidades de diferentes tipos de motoristas (inexperientes, idosos, portadores de limitações, etc.). Vislumbra-se que a aplicação em larga escala desse tipo de tecnologia, em um futuro próximo, certamente reduzirá drasticamente a quantidade de pessoas feridas e mortas em acidentes automobilísticos em estradas e em ambientes urbanos. Nesse contexto, este projeto de pesquisa teve como objetivo proporcionar informações relativas ao ambiente ao redor do veículo, ao sistema de controle e de tomada de decisão embarcado no veículo autônomo. As informações mais básicas fornecidas são as posições dos objetos (obstáculos) ao redor do veículo; além disso, informações como o tipo de objeto (ou seja, sua classificação em carros, pedestres, postes e a própria rua mesma), assim como o tamanho deles. Os dados do ambiente são adquiridos através do emprego de uma câmera e um Velodyne LiDAR. Um estudo do tipo ceiling foi usado para simular a metodologia da detecção dos obstáculos. Estima-se que , após realizar o estudo, que analisar regiões especificas da imagem, chamadas de regiões de interesse, onde é mais provável encontrar um obstáculo, é o melhor jeito de melhorar o sistema de reconhecimento. Observou-se na implementação da fusão dos sensores que encontrar regiões de interesse usando LiDAR, e classificá-las usando visão artificial fornece um melhor resultado na hora de compará-lo com os resultados ao usar apenas câmera ou LiDAR. Obteve-se uma classificação com precisão de 100% para pedestres e 92,3% para carros, rodando em uma frequência de 6 Hz. A fusão dos sensores também forneceu um método para estimar a estrada mesmo quando esta tinha sombra ou faixas de cor. Em geral, a classificação baseada em visão artificial e LiDAR mostrou uma solução para detecção de objetos em várias escalas e mesmo para o problema da iluminação não uniforme do ambiente.

Стилі APA, Harvard, Vancouver, ISO та ін.

21

Riffel, Alvin Daniel. "Effects of a dialogical argumentation based instruction on grade 9 learners' conceptions of a meteorological concept: Cold Fronts in the Western Cape, South Africa." Thesis, University of Western Cape, 2012. http://etd.uwc.ac.za/index.php?module=etd&action=viewtitle&id=gen8Srv25Nme4_6262_1384164748.

Повний текст джерела

Анотація:

This study looks at the effects of a dialogical argumentation instructional model (DAIM) on grade 9 learners understanding of selected meteorological concepts: Cold fronts in the Western Cape of South Africa. Using a quasi-experimental research design model, the study employed both quantitative and qualitative (so-called &lsquo
mixed methods&rsquo
) to collect data in a public secondary school in Cape Town, in the Western Cape Province. A survey questionnaire on attitudes and perceptions towards high school as well as conceptions of weather was administered before the main study to give the researcher baseline information and to develop pilot instruments to use in the main study.

The study employed a dialogical instructional model (DAIM) with an experimental group of learners exposed to the intervention, and recorded differences from a control group which had no intervention. Learners from the two groups were exposed to a meteorological literacy test evaluation before and after the DAIM intervention. The results from the two groups were then compared and analysed according to the two theoretical frameworks that underpin the study namely: Toulmin&rsquo
s Argumentation Pattern - TAP (Toulmin, 1958) and Contiguity Argumentation Theory - CAT (Ogunniyi, 1997).

Further analyses were conducted on learners&rsquo
beliefs and indigenous knowledge, according to their conceptual understanding of weather related concepts used in the current NCS (National Curriculum Statement).
After completing the study some interesting findings were made and based on these findings certain recommendations were suggested on how to implement a DAIM-model into classroom teaching using Indigenous Knowledge (IK). These recommendations are suggestions to plot the way towards developing a science&ndash
IK curriculum for the Natural Sciences subjects in South African schools.

Стилі APA, Harvard, Vancouver, ISO та ін.

22

Moohialdin, Ammar. "A real-time worker activity intensity identification system for construction workers under hot and humid weather conditions." Thesis, Queensland University of Technology, 2020. https://eprints.qut.edu.au/206448/1/Ammar_Moohialdin_Thesis.pdf.

Повний текст джерела

Анотація:

This research examined a novel real-time, non-intrusive activity intensity identification system that approximate site activity intensity levels and their associated risks under hot and humid weather conditions. The research revealed that the activity intensity identification system provides real-time, non-intrusive measurements and early warning signs at the crew level. Physical work and site activities also contribute to high activity intensity levels, while the combined effects of activity intensity and hot and humid weather conditions have substantial direct and indirect heat-related risks. The findings contribute to innovative methods for real-site measurements and reinforce early warning signs to take heat-related interventions at the right time.

Стилі APA, Harvard, Vancouver, ISO та ін.

23

Duthon, Pierre. "Descripteurs d'images pour les systèmes de vision routiers en situations atmosphériques dégradées et caractérisation des hydrométéores." Thesis, Université Clermont Auvergne‎ (2017-2020), 2017. http://www.theses.fr/2017CLFAC065/document.

Повний текст джерела

Анотація:

Les systèmes de vision artificielle sont de plus en plus présents en contexte routier. Ils sont installés sur l'infrastructure, pour la gestion du trafic, ou placés à l'intérieur du véhicule, pour proposer des aides à la conduite. Dans les deux cas, les systèmes de vision artificielle visent à augmenter la sécurité et à optimiser les déplacements. Une revue bibliographique retrace les origines et le développement des algorithmes de vision artificielle en contexte routier. Elle permet de démontrer l'importance des descripteurs d'images dans la chaîne de traitement des algorithmes. Elle se poursuit par une revue des descripteurs d'images avec une nouvelle approche source de nombreuses analyses, en les considérant en parallèle des applications finales. En conclusion, la revue bibliographique permet de déterminer quels sont les descripteurs d'images les plus représentatifs en contexte routier. Plusieurs bases de données contenant des images et les données météorologiques associées (ex : pluie, brouillard) sont ensuite présentées. Ces bases de données sont innovantes car l'acquisition des images et la mesure des conditions météorologiques sont effectuées en même temps et au même endroit. De plus, des capteurs météorologiques calibrés sont utilisés. Chaque base de données contient différentes scènes (ex: cible noir et blanc, piéton) et divers types de conditions météorologiques (ex: pluie, brouillard, jour, nuit). Les bases de données contiennent des conditions météorologiques naturelles, reproduites artificiellement et simulées numériquement. Sept descripteurs d'images parmi les plus représentatifs du contexte routier ont ensuite été sélectionnés et leur robustesse en conditions de pluie évaluée. Les descripteurs d'images basés sur l'intensité des pixels ou les contours verticaux sont sensibles à la pluie. A l'inverse, le descripteur de Harris et les descripteurs qui combinent différentes orientations sont robustes pour des intensités de pluie de 0 à 30 mm/h. La robustesse des descripteurs d'images en conditions de pluie diminue lorsque l'intensité de pluie augmente. Finalement, les descripteurs les plus sensibles à la pluie peuvent potentiellement être utilisés pour des applications de détection de la pluie par caméra.Le comportement d'un descripteur d'images en conditions météorologiques dégradées n'est pas forcément relié à celui de la fonction finale associée. Pour cela, deux détecteurs de piéton ont été évalués en conditions météorologiques dégradées (pluie, brouillard, jour, nuit). La nuit et le brouillard sont les conditions qui ont l'impact le plus important sur la détection des piétons. La méthodologie développée et la base de données associée peuvent être utilisées à nouveau pour évaluer d'autres fonctions finales (ex: détection de véhicule, détection de signalisation verticale).En contexte routier, connaitre les conditions météorologiques locales en temps réel est essentiel pour répondre aux deux enjeux que sont l'amélioration de la sécurité et l'optimisation des déplacements. Actuellement, le seul moyen de mesurer ces conditions le long des réseaux est l'installation de stations météorologiques. Ces stations sont coûteuses et nécessitent une maintenance particulière. Cependant, de nombreuses caméras sont déjà présentes sur le bord des routes. Une nouvelle méthode de détection des conditions météorologiques utilisant les caméras de surveillance du trafic est donc proposée. Cette méthode utilise des descripteurs d'images et un réseau de neurones. Elle répond à un ensemble de contraintes clairement établies afin de pouvoir détecter l'ensemble des conditions météorologiques en temps réel, mais aussi de pourvoir proposer plusieurs niveaux d'intensité. La méthode proposée permet de détecter les conditions normales de jour, de nuit, la pluie et le brouillard. Après plusieurs phases d'optimisation, la méthode proposée obtient de meilleurs résultats que ceux obtenus dans la littérature, pour des algorithmes comparables
Computer vision systems are increasingly being used on roads. They can be installed along infrastructure for traffic monitoring purposes. When mounted in vehicles, they perform driver assistance functions. In both cases, computer vision systems enhance road safety and streamline travel.A literature review starts by retracing the introduction and rollout of computer vision algorithms in road environments, and goes on to demonstrate the importance of image descriptors in the processing chains implemented in such algorithms. It continues with a review of image descriptors from a novel approach, considering them in parallel with final applications, which opens up numerous analytical angles. Finally the literature review makes it possible to assess which descriptors are the most representative in road environments.Several databases containing images and associated meteorological data (e.g. rain, fog) are then presented. These databases are completely original because image acquisition and weather condition measurement are at the same location and the same time. Moreover, calibrated meteorological sensors are used. Each database contains different scenes (e.g. black and white target, pedestrian) and different kind of weather (i.e. rain, fog, daytime, night-time). Databases contain digitally simulated, artificial and natural weather conditions.Seven of the most representative image descriptors in road context are then selected and their robustness in rainy conditions is evaluated. Image descriptors based on pixel intensity and those that use vertical edges are sensitive to rainy conditions. Conversely, the Harris feature and features that combine different edge orientations remain robust for rainfall rates ranging in 0 – 30 mm/h. The robustness of image features in rainy conditions decreases as the rainfall rate increases. Finally, the image descriptors most sensitive to rain have potential for use in a camera-based rain classification application.The image descriptor behaviour in adverse weather conditions is not necessarily related to the associated final function one. Thus, two pedestrian detectors were assessed in degraded weather conditions (rain, fog, daytime, night-time). Night-time and fog are the conditions that have the greatest impact on pedestrian detection. The methodology developed and associated database could be reused to assess others final functions (e.g. vehicle detection, traffic sign detection).In road environments, real-time knowledge of local weather conditions is an essential prerequisite for addressing the twin challenges of enhancing road safety and streamlining travel. Currently, the only mean of quantifying weather conditions along a road network requires the installation of meteorological stations. Such stations are costly and must be maintained; however, large numbers of cameras are already installed on the roadside. A new method that uses road traffic cameras to detect weather conditions has therefore been proposed. This method uses a combination of a neural network and image descriptors applied to image patches. It addresses a clearly defined set of constraints relating to the ability to operate in real-time and to classify the full spectrum of meteorological conditions and grades them according to their intensity. The method differentiates between normal daytime, rain, fog and normal night-time weather conditions. After several optimisation steps, the proposed method obtains better results than the ones reported in the literature for comparable algorithms

Стилі APA, Harvard, Vancouver, ISO та ін.

24

Williams, Stephen Vincent. "Visual arctic navigation: techniques for autonomous agents in glacial environments." Diss., Georgia Institute of Technology, 2011. http://hdl.handle.net/1853/41135.

Повний текст джерела

Анотація:

Arctic regions are thought to be more sensitive to climate change fluctuations, making weather data from these regions more valuable for climate modeling. Scientists have expressed an interest in deploying a robotic sensor network in these areas, minimizing the exposure of human researchers to the harsh environment, while allowing dense, targeted data collection to commence. For any such robotic system to be successful, a certain set of base navigational functionality must be developed. Further, these navigational algorithms must rely on the types of low-cost sensors that would be viable for use in a multi-agent system. A set of vision-based processing techniques have been proposed, which augment current robotic technologies for use in glacial terrains. Specifically, algorithms for estimating terrain traversability, robot localization, and terrain reconstruction have been developed which use data collected exclusively from a single camera and other low-cost robotic sensors. For traversability assessment, a custom algorithm was developed that uses local scale surface texture to estimate the terrain slope. Additionally, a horizon line estimation system has been proposed that is capable of coping with low-contrast, ambiguous horizons. For localization, a monocular simultaneous localization and mapping (SLAM) filter has been fused with consumer-grade GPS measurements to produce full robot pose estimates that do not drift over long traverses. Finally, a terrain reconstruction methodology has been proposed that uses a Gaussian process framework to incorporate sparse SLAM landmarks with dense slope estimates to produce a single, consistent terrain model. These algorithms have been tested within a custom glacial terrain computer simulation and against multiple data sets acquired during glacial field trials. The results of these tests indicate that vision is a viable sensing modality for autonomous glacial robotics, despite the obvious challenges presented by low-contrast glacial scenery. The findings of this work are discussed within the context of the larger arctic sensor network project, and a direction for future work is recommended.

Стилі APA, Harvard, Vancouver, ISO та ін.

25

Dahmane, Khouloud. "Analyse d'images par méthode de Deep Learning appliquée au contexte routier en conditions météorologiques dégradées." Thesis, Université Clermont Auvergne‎ (2017-2020), 2020. http://www.theses.fr/2020CLFAC020.

Повний текст джерела

Анотація:

De nos jours, les systèmes de vision sont de plus en plus utilisés dans le contexte routier. Ils permettent ainsi d'assurer la sécurité et faciliter la mobilité. Ces systèmes de vision sont généralement affectés par la dégradation des conditions météorologiques en présence de brouillard ou de pluie forte, phénomènes limitant la visibilité et réduisant ainsi la qualité des images. Afin d'optimiser les performances des systèmes de vision, il est nécessaire de disposer d'un système de détection fiable de ces conditions météorologiques défavorables.Il existe des capteurs météorologiques dédiés à la mesure physique, mais ils sont coûteux. Ce problème peut être résolu en utilisant les caméras qui sont déjà installées sur les routes. Ces dernières peuvent remplir simultanément deux fonctions : l'acquisition d'images pour les applications de surveillance et la mesure physique des conditions météorologiques au lieu des capteurs dédiés. Suite au grand succès des réseaux de neurones convolutifs (CNN) dans la classification et la reconnaissance d'images, nous avons utilisé une méthode d'apprentissage profond pour étudier le problème de la classification météorologique. L'objectif de notre étude est de chercher dans un premier temps à mettre au point un classifieur du temps, qui permet de discriminer entre temps « normal », brouillard et pluie. Dans un deuxième temps, une fois la classe connue, nous cherchons à développer un modèle de mesure de la distance de visibilité météorologique du brouillard. Rappelons que l'utilisation des CNN exige l'utilisation de bases de données d'apprentissage et de test. Pour cela, deux bases de données ont été utilisées, "Cerema-AWP database" (https://ceremadlcfmds.wixsite.com/cerema-databases), et la base "Cerema-AWH database", en cours d'acquisition depuis 2017 sur le site de la Fageole sur l'autoroute A75. Chaque image des deux bases est labellisée automatiquement grâce aux données météorologiques relevées sur le site permettant de caractériser diverses gammes de pluie et de brouillard. La base Cerema-AWH, qui a été mise en place dans le cadre de nos travaux, contient cinq sous-bases : conditions normales de jour, brouillard fort, brouillard faible, pluie forte et pluie faible. Les intensités de pluie varient de 0 mm/h à 70 mm/h et les visibilités météorologiques de brouillard varient entre 50m et 1800m. Parmi les réseaux de neurones connus et qui ont montré leur performance dans le domaine de la reconnaissance et la classification, nous pouvons citer LeNet, ResNet-152, Inception-v4 et DenseNet-121. Nous avons appliqué ces réseaux dans notre système de classification des conditions météorologiques dégradées. En premier lieu, une étude justificative de l'usage des réseaux de neurones convolutifs est effectuée. Elle étudie la nature de la donnée d'entrée et les hyperparamètres optimaux qu'il faut utiliser pour aboutir aux meilleurs résultats. Ensuite, une analyse des différentes composantes d'un réseau de neurones est menée en construisant une architecture instrumentale de réseau de neurones. La classification des conditions météorologiques avec les réseaux de neurones profonds a atteint un score de 83% pour une classification de cinq classes et 99% pour une classification de trois classes.Ensuite, une analyse sur les données d'entrée et de sortie a été faite permettant d'étudier l'impact du changement de scènes et celui du nombre de données d'entrée et du nombre de classes météorologiques sur le résultat de classification.Enfin, une méthode de transfert de bases de données a été appliquée. Cette méthode permet d'étudier la portabilité du système de classification des conditions météorologiques d'un site à un autre. Un score de classification de 63% a été obtenu en faisant un transfert entre une base publique et la base Cerema-AWH. (...)
Nowadays, vision systems are becoming more and more used in the road context. They ensure safety and facilitate mobility. These vision systems are generally affected by the degradation of weather conditions, like heavy fog or strong rain, phenomena limiting the visibility and thus reducing the quality of the images. In order to optimize the performance of the vision systems, it is necessary to have a reliable detection system for these adverse weather conditions.There are meteorological sensors dedicated to physical measurement, but they are expensive. Since cameras are already installed on the road, they can simultaneously perform two functions: image acquisition for surveillance applications and physical measurement of weather conditions instead of dedicated sensors. Following the great success of convolutional neural networks (CNN) in classification and image recognition, we used a deep learning method to study the problem of meteorological classification. The objective of our study is to first seek to develop a classifier of time, which discriminates between "normal" conditions, fog and rain. In a second step, once the class is known, we seek to develop a model for measuring meteorological visibility.The use of CNN requires the use of train and test databases. For this, two databases were used, "Cerema-AWP database" (https://ceremadlcfmds.wixsite.com/cerema-databases), and the "Cerema-AWH database", which has been acquired since 2017 on the Fageole site on the highway A75. Each image of the two bases is labeled automatically thanks to meteorological data collected on the site to characterize various levels of precipitation for rain and fog.The Cerema-AWH base, which was set up as part of our work, contains 5 sub-bases: normal day conditions, heavy fog, light fog, heavy rain and light rain. Rainfall intensities range from 0 mm/h to 70mm/h and fog weather visibilities range from 50m to 1800m. Among the known neural networks that have demonstrated their performance in the field of recognition and classification, we can cite LeNet, ResNet-152, Inception-v4 and DenseNet-121. We have applied these networks in our adverse weather classification system. We start by the study of the use of convolutional neural networks. The nature of the input data and the optimal hyper-parameters that must be used to achieve the best results. An analysis of the different components of a neural network is done by constructing an instrumental neural network architecture. The conclusions drawn from this analysis show that we must use deep neural networks. This type of network is able to classify five meteorological classes of Cerema-AWH base with a classification score of 83% and three meteorological classes with a score of 99%Then, an analysis of the input and output data was made to study the impact of scenes change, the input's data and the meteorological classes number on the classification result.Finally, a database transfer method is developed. We study the portability from one site to another of our adverse weather conditions classification system. A classification score of 63% by making a transfer between a public database and Cerema-AWH database is obtained.After the classification, the second step of our study is to measure the meteorological visibility of the fog. For this, we use a neural network that generates continuous values. Two fog variants were tested: light and heavy fog combined and heavy fog (road fog) only. The evaluation of the result is done using a correlation coefficient R² between the real values and the predicted values. We compare this coefficient with the correlation coefficient between the two sensors used to measure the weather visibility on site. Among the results obtained and more specifically for road fog, the correlation coefficient reaches a value of 0.74 which is close to the physical sensors value (0.76)

Стилі APA, Harvard, Vancouver, ISO та ін.

26

Bri, Molinero Diana. "ESTUDIO DEL EFECTO DE FACTORES EXTERNOS SOBRE LAS REDES WLAN Y DISEÑO DE UN ALGORITMO COGNITIVO ENERGÉTICAMENTE EFICIENTE." Doctoral thesis, Universitat Politècnica de València, 2015. http://hdl.handle.net/10251/53450.

Повний текст джерела

Анотація:

[EN] Nowadays there are many works which analyze and seek to improve the performance of Wireless Local Area Networks (WLANs) from different perspectives. A great deal of them is focused on design aspects, such as frequency distribution or channel assignment. Therefore, as these features have already been widely studied, my efforts have been directed to study other conditions that also could affect their performance and that have not been analyzed in depth yet. The main goal of this Ph.D. dissertation has been to perform a detailed study that researches the weather's impact on the performance of WLANs IEEE 802.11b/g. Two different WLAN scenarios have been analyzed to validate the results and to find precise relations. From conclusions of these previous analysis, the second objective has been to design a cognitive protocol that based on weather conditions and network performance parameters, allows networks to adjust their transmission features in order to overcome such impact. In order to conduct this study, firstly it was necessary to study which statistical methods could be used to extract the level of correlation between performance parameters of networks and weather conditions running at the same time. Secondly, I had to know which performance parameters the outdoor WLAN of Universitat Politècnica de València (UPV) could provide, and select them according to my objective. Then, I defined the period of time in which these parameters were gathered periodically. The next step was to select and collect the weather conditions from a close weather station during the same period of time. Finally, I had to perform a detailed pre-processing to put all of the volume of data in order and data were statistically analyzed. Results were successful; however there were several problems due to the variability derived from a real WLAN scenario. Therefore, an experimental setup was required in order to check the obtained results. It entailed to design and to develop an outdoor point-to-multipoint IEEE 802.11b/g link and to analyze again the weather's impact. Multiple points were considered in order to take into account different distances in the performed evaluation and to examine the behavior of different modulation schemes working under the same weather conditions. From these results, a cognitive algorithm was designed in order to reduce the weather's impact on IEEE 802.11b/g networks. One key aspect was to ensure it was energy efficient. This protocol was simulated and the obtained results were satisfactory in terms of both energy efficiency and network performance. To conclude, other external factor to WLANs studied in this Ph.D thesis has been the specific absorption rate. It deals with a current public health worry because it is used to measure the body tissue exposure to electromagnetic fields. Obviously, signal absorption by human bodies affects to the performance of WLANs and so, this parameter should be also taken into account when deploying efficient networks. For this reason, this study has been also included in this thesis.
[ES] Hoy en día existen muchos trabajos que analizan e intentan mejorar el rendimiento de las redes de área local inalámbricas desde diferentes perspectivas. Gran parte de estos trabajos se centran en aspectos de diseño, como son la distribución de frecuencias o la asignación de canales. Por lo tanto, como estos aspectos ya han sido ampliamente estudiados, los esfuerzos de esta tesis se han dirigido a estudiar otros factores que también podrían afectar a su rendimiento y que no han sido analizadas en profundidad todavía. El objetivo principal de esta tesis doctoral ha sido realizar un estudio detallado que analice el impacto de las condiciones meteorológicas sobre el rendimiento de las redes IEEE 802.11b/g. Para realizar este estudio, se han analizado dos escenarios reales con el fin de verificar los resultados y encontrar relaciones precisas. A partir de las conclusiones de estos análisis previos, el segundo objetivo ha sido diseñar un algoritmo cognitivo que, en base a las condiciones meteorológicas y a los parámetros de rendimiento de red, permita a las redes ajustar sus características de transmisión con el fin de superar tal impacto. Con el fin de llevar a cabo este estudio, primero fue necesario estudiar qué métodos estadísticos podían ser utilizados para extraer el nivel de correlación entre los parámetros de rendimiento de las redes y las condiciones meteorológicas del entorno. En segundo lugar, se tuvo que analizar qué parámetros de rendimiento de red se podían extraer de la red exterior de la UPV y seleccionarlos de acuerdo con el objetivo perseguido. A continuación, se definió el periodo de tiempo durante el cual se almacenarían los parámetros seleccionados de forma periódica. El siguiente paso fue seleccionar y almacenar las condiciones meteorológicas de una estación cercana durante el mismo periodo de tiempo. Finalmente, se realizó un preprocesado detallado con el fin de poner en orden todo el volumen de datos y se analizaron estadísticamente. Los resultados fueron exitosos, sin embargo aparecieron varios problemas por el hecho de estudiar una red real muy variable. Por lo tanto, se tuvo que desarrollar un escenario experimental con el fin de verificar los resultados. Para ello se diseñó y desarrolló un enlace exterior IEEE 802.11b/g punto a multipunto, y se analizó de nuevo el impacto de las condiciones meteorológicas. Se consideró un enlace multipunto para analizar también cómo influía el impacto del tiempo según la distancia y los diferentes esquemas de modulación. A partir de los resultados, se diseñó un algoritmo cognitivo energéticamente eficiente con el fin de reducir el impacto de los fenómenos meteorológicos en las redes IEEE 802.11b/g. Dicho algoritmo ha sido simulado y los resultados obtenidos han sido satisfactorios, tanto en términos de eficiencia energética como de rendimiento de la red. Para concluir, otro factor externo que se ha estudiado en esta tesis ha sido la tasa de absorción específica. Este parámetro está relacionado con una de las grandes preocupaciones actuales en cuanto a salud pública, ya que se utiliza para medir la exposición de los tejidos del cuerpo humano a los campos electromagnéticos. Obviamente, la absorción de señal por parte del cuerpo humano afecta a las redes y, por lo tanto, este parámetro se debería tener en cuenta a la hora de diseñar redes eficientes. Por esta razón se ha incluido en esta tesis doctoral.
[CAT] Actualment hi ha molts treballs que analitzen i intenten millorar el rendiment de les xarxes d'àrea local sense fils des de diferents perspectives. Gran part d'aquests treballs es focalitzen en aspectes de disseny, com són la distribució de freqüències o l'assignació de canals. Per tant, com aquests aspectes ja han sigut àmpliament estudiats, els esforços d'aquesta tesi doctoral s'han dirigit a estudiar altres factors que també podrien afectar al seu rendiment i que encara no han sigut analitzats amb profunditat. L'objectiu principal d'aquesta tesi doctoral ha sigut realitzar un estudi minuciós per analitzar l'impacte de les condicions meteorològiques sobre el rendiment de les xarxes IEEE 802.11b/g. Per a realitzar aquest estudi s'han analitzat dos escenaris reals per tal de verificar els resultats i trobar relacions precises. A partir de les conclusions d'aquests anàlisis previ, el següent objectiu ha sigut dissenyar un algoritme cognitiu que, en base a les condicions meteorològiques i als paràmetres de rendiment de la xarxa, permeti a les xarxes ajustar les seues característiques de transmissió per tal de superar tal impacte. Per tal de dur a terme aquest estudi, primer va ser necessari estudiar quins mètodes estadístics podien ser utilitzats per extraure el nivell de correlació entre els paràmetres de rendiment de les xarxes i les condicions meteorològiques de l'entorn. En segon lloc, es va haver d'analitzar quins paràmetres de rendiment es podien extraure de la xarxa exterior de la UPV i es van seleccionar d'acord a l'objectiu plantejat. A continuació, es va definir el període temporal al llarg del qual s'emmagatzemarien els paràmetres seleccionats de manera periòdica. El següent pas va ser seleccionar i emmagatzemar les condicions meteorològiques d'una estació propera durant el mateix període de temps. Finalment, es va realitzar un preprocessat per tal de posar en ordre tot el volum de dades i es van analitzar estadísticament. Els resultats van ser exitosos, però van aparèixer diversos problemes pel fet d'estudiar una xarxa real molt variable. Per tant, es va haver de desenvolupar un escenari experimental amb l'objectiu de verificar els resultats. Per aquesta raó es va dissenyar i implementar un enllaç exterior IEEE 802.11b/g punt a multipunt, i es va analitzar de nou l'impacte de les condicions meteorològiques. Es va considerar un enllaç multipunt per tal de d'analitzar també com influïa el impacte del temps segons la distància i els diferents esquemes de modulació. A partir d'aquests resultats, es va dissenyar un algoritme cognitiu energèticament eficient per tal de reduir l'impacte dels fenòmens meteorològics sobre les xarxes IEEE 802.11b/g. Aquest algoritme va ser simulat i els resultats obtinguts van ser satisfactoris, tant en termes d'eficiència energètica com de rendiment de la xarxa. va comprovar que la proposta aporta millores. Per concloure, un altre factor extern que s'ha estudiat en aquesta tesi doctoral ha sigut la taxa d'absorció específica. Aquest paràmetre està relacionat amb una de les preocupacions actuals pel que fa a la salut pública, ja que s'utilitza per a mesurar l'exposició dels teixits del cos humà als camps electromagnètics. Òbviament, aquesta absorció de la senyal afecta el rendiment de les xarxes i, per això, aquest paràmetre s'hauria de tenir en compte a l'hora d'implementar futures xarxes sense fils eficients. Per aquesta raó s'ha inclòs en aquesta tesi doctoral.
Bri Molinero, D. (2015). ESTUDIO DEL EFECTO DE FACTORES EXTERNOS SOBRE LAS REDES WLAN Y DISEÑO DE UN ALGORITMO COGNITIVO ENERGÉTICAMENTE EFICIENTE [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/53450
TESIS

Стилі APA, Harvard, Vancouver, ISO та ін.

27

Ellingson, Gary James. "Cooperative Navigation of Fixed-Wing Micro Air Vehicles in GPS-Denied Environments." BYU ScholarsArchive, 2019. https://scholarsarchive.byu.edu/etd/8706.

Повний текст джерела

Анотація:

Micro air vehicles have recently gained popularity due to their potential as autonomous systems. Their future impact, however, will depend in part on how well they can navigate in GPS-denied and GPS-degraded environments. In response to this need, this dissertation investigates a potential solution for GPS-denied operations called relative navigation. The method utilizes keyframe-to-keyframe odometry estimates and their covariances in a global back end that represents the global state as a pose graph. The back end is able to effectively represent nonlinear uncertainties and incorporate opportunistic global constraints. The GPS-denied research community has, for the most part, neglected to consider fixed-wing aircraft. This dissertation enables fixed-wing aircraft to utilize relative navigation by accounting for their sensing requirements. The development of an odometry-like, front-end, EKF-based estimator that utilizes only a monocular camera and an inertial measurement unit is presented. The filter uses the measurement model of the multi-state-constraint Kalman filter and regularly performs relative resets in coordination with keyframe declarations. In addition to the front-end development, a method is provided to account for front-end velocity bias in the back-end optimization. Finally a method is presented for enabling multiple vehicles to improve navigational accuracy by cooperatively sharing information. Modifications to the relative navigation architecture are presented that enable decentralized, cooperative operations amidst temporary communication dropouts. The proposed framework also includes the ability to incorporate inter-vehicle measurements and utilizes a new concept called the coordinated reset, which is necessary for optimizing the cooperative odometry and improving localization. Each contribution is demonstrated through simulation and/or hardware flight testing. Simulation and Monte-Carlo testing is used to show the expected quality of the results. Hardware flight-test results show the front-end estimator performance, several back-end optimization examples, and cooperative GPS-denied operations.

Стилі APA, Harvard, Vancouver, ISO та ін.

28

Rousset, Xavier. "La tarification dynamique, l'utile et le juste Seasonal factors and marketing mix: Literature survey and proposed guidelines An analytical framework for retailer price and advertising decisions for products with temperature-sensitive demand The impact of outdoor temperature on pricing and advertising policies for weather-sensitive products Tarification dynamique en ligne et éthicalité perçue par le consommateur : synthèse et voies de recherche Designing algorithmic dynamic pricing from an ethical perspective Are consumers vulnerable to algorithmic dynamic pricing? An empirical investigation." Thesis, Sorbonne Paris Cité, 2019. http://www.theses.fr/2019USPCB039.

Повний текст джерела

Анотація:

Cette thèse regroupe différents travaux de recherche sur la tarification dynamique. L'objectif de la thèse, située à l'interface des sciences économiques, des sciences de gestion et des sciences politiques, est double : d'une part, étudier les déterminants et les conditions d'utilisation de la tarification dynamique au niveau de la firme dans une perspective de maximation de ses profits et, d'autre part, de montrer comment, à un niveau collectif, la prise en compte des questions éthiques dans l'étude de la tarification dynamique permet de mieux en comprendre la portée. Nos contributions, à la fois théoriques et empiriques, sont présentées en deux parties. La partie 1, axée sur l'efficacité économique (point de vue de l'utile), regroupe des questionnements sur les considérations de maximation du bénéfice liées à la tarification dynamique. A partir de l'étude de produits dits météo-sensibles dans les canaux de distribution physique, nous présentons une revue de littérature qui introduit l'adaptation dynamique du prix à des facteurs influençant la demande et nous proposons un modèle théorique d'adaptation dynamique du prix dans le temps suivant la température. Nous complétons cette approche théorique, par une étude empirique qui approfondit comment la tarification, exercée de manière dynamique du point de vue de la firme en réaction à des facteurs extérieurs, lui permet de maximiser ses intérêts. La partie 2 regroupe des travaux sur les considérations éthiques liées à la tarification dynamique (point de vue du juste). En se focalisant sur les canaux de distribution en ligne, nous discutons, sur un plan théorique, les incidences possibles de la tarification dynamique sur la perception éthique par le consommateur, en mettant en évidence les éventuels risques d'injustice ou de vulnérabilité que cette stratégie de fixation du prix soulève. D'un point de vue empirique, nous approfondissons l'analyse des déterminants de la perception éthique de la tarification dynamique en ligne par le consommateur, notamment en fonction des conditions de son paramétrage, ainsi que les dimensions de vulnérabilité qui préoccupent les consommateurs. La conclusion de la thèse regroupe des pistes de recherche futures portant sur l'approfondissement de la mesure de l'éthique perçue, sur les potentialités de l'hybridation de la science économique avec l'éthique sur un sujet comme celui de la tarification dynamique et sur les considérations que nous avons entrevues sur le lien entre la tarification dynamique et la révélation de la valeur d'échange (point de vue du vrai)
This PhD thesis brings together different research projects on dynamic pricing. The objective of the thesis, located at the interface of economics, management sciences and political sciences, is twofold: first, to study the determinants and conditions of use of dynamic pricing at the level of firm in a perspective of maximizing its profits and, on the other hand, to show how, at a collective level, the consideration of ethical issues in the study of dynamic pricing allows a better understanding of its scope. Our contributions, both theoretical and empirical, are presented in two parts. Part 1 focuses on economic efficiency (point of view of the useful), and asks questions about the maximization of profit considerations related to dynamic pricing. From the study of so-called weather-sensitive products in the physical distribution channels, we present a literature review that introduces the dynamic adaptation of the price to factors influencing the demand and we propose a theoretical model of dynamic adaptation of the price in time following the temperature. We complete this theoretical approach with an empirical study that examines how pricing, exercised dynamically from the firm's point of view in response to external factors, allows it to maximize its interests. Part 2 brings together work on ethical considerations related to dynamic pricing (the point of view of the right). Focusing on online distribution channels, we discuss, on a theoretical level, the potential impact of dynamic pricing on consumers' ethical perception, highlighting potential risks of unfairness or vulnerability that price fixing raises. From an empirical point of view, we thoroughly analyse the determinants of the ethical perception of online dynamic pricing by the consumer, in particular according to the conditions of its setting, as well as the dimensions of vulnerability that concern consumers.The conclusion of the thesis brings together future lines of research on the deepening of the measurement of perceived ethics, on the potentialities of the hybridization of economic science with ethics on a subject such as dynamic pricing and on the considerations we have seen on the link between dynamic pricing and the revelation of exchange value (point of view of the true)

Стилі APA, Harvard, Vancouver, ISO та ін.

29

Wheeler, David Orton. "Relative Navigation of Micro Air Vehicles in GPS-Degraded Environments." BYU ScholarsArchive, 2017. https://scholarsarchive.byu.edu/etd/6609.

Повний текст джерела

Анотація:

Most micro air vehicles rely heavily on reliable GPS measurements for proper estimation and control, and therefore struggle in GPS-degraded environments. When GPS is not available, the global position and heading of the vehicle is unobservable. This dissertation establishes the theoretical and practical advantages of a relative navigation framework for MAV navigation in GPS-degraded environments. This dissertation explores how the consistency, accuracy, and stability of current navigation approaches degrade during prolonged GPS dropout and in the presence of heading uncertainty. Relative navigation (RN) is presented as an alternative approach that maintains observability by working with respect to a local coordinate frame. RN is compared with several current estimation approaches in a simulation environment and in hardware experiments. While still subject to global drift, RN is shown to produce consistent state estimates and stable control. Estimating relative states requires unique modifications to current estimation approaches. This dissertation further provides a tutorial exposition of the relative multiplicative extended Kalman filter, presenting how to properly ensure observable state estimation while maintaining consistency. The filter is derived using both inertial and body-fixed state definitions and dynamics. Finally, this dissertation presents a series of prolonged flight tests, demonstrating the effectiveness of the relative navigation approach for autonomous GPS-degraded MAV navigation in varied, unknown environments. The system is shown to utilize a variety of vision sensors, work indoors and outdoors, run in real-time with onboard processing, and not require special tuning for particular sensors or environments. Despite leveraging off-the-shelf sensors and algorithms, the flight tests demonstrate stable front-end performance with low drift. The flight tests also demonstrate the onboard generation of a globally consistent, metric, and localized map by identifying and incorporating loop-closure constraints and intermittent GPS measurements. With this map, mission objectives are shown to be autonomously completed.

Стилі APA, Harvard, Vancouver, ISO та ін.

30

Svoboda, Ondřej. "Analýza vlastností stereokamery ZED ve venkovním prostředí." Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2019. http://www.nusl.cz/ntk/nusl-399416.

Повний текст джерела

Анотація:

The Master thesis is focused on analyzing stereo camera ZED in the outdoor environment. There is compared ZEDfu visual odometry with commonly used methods like GPS or wheel odometry. Moreover, the thesis includes analyses of SLAM in the changeable outdoor environment, too. The simultaneous mapping and localization in RTAB-Map were processed separately with SIFT and BRISK descriptors. The aim of this master thesis is to analyze the behaviour ZED camera in the outdoor environment for future implementation in mobile robotics.

Стилі APA, Harvard, Vancouver, ISO та ін.

31

Jackson, James Scott. "Enabling Autonomous Operation of Micro Aerial Vehicles Through GPS to GPS-Denied Transitions." BYU ScholarsArchive, 2019. https://scholarsarchive.byu.edu/etd/8709.

Повний текст джерела

Анотація:

Micro aerial vehicles and other autonomous systems have the potential to truly transform life as we know it, however much of the potential of autonomous systems remains unrealized because reliable navigation is still an unsolved problem with significant challenges. This dissertation presents solutions to many aspects of autonomous navigation. First, it presents ROSflight, a software and hardware architure that allows for rapid prototyping and experimentation of autonomy algorithms on MAVs with lightweight, efficient flight control. Next, this dissertation presents improvments to the state-of-the-art in optimal control of quadrotors by utilizing the error-state formulation frequently utilized in state estimation. It is shown that performing optimal control directly over the error-state results in a vastly more computationally efficient system than competing methods while also dealing with the non-vector rotation components of the state in a principled way. In addition, real-time robust flight planning is considered with a method to navigate cluttered, potentially unknown scenarios with real-time obstacle avoidance. Robust state estimation is a critical component to reliable operation, and this dissertation focuses on improving the robustness of visual-inertial state estimation in a filtering framework by extending the state-of-the-art to include better modeling and sensor fusion. Further, this dissertation takes concepts from the visual-inertial estimation community and applies it to tightly-coupled GNSS, visual-inertial state estimation. This method is shown to demonstrate significantly more reliable state estimation than visual-inertial or GNSS-inertial state estimation alone in a hardware experiment through a GNSS-GNSS denied transition flying under a building and back out into open sky. Finally, this dissertation explores a novel method to combine measurements from multiple agents into a coherent map. Traditional approaches to this problem attempt to solve for the position of multiple agents at specific times in their trajectories. This dissertation instead attempts to solve this problem in a relative context, resulting in a much more robust approach that is able to handle much greater intial error than traditional approaches.

Стилі APA, Harvard, Vancouver, ISO та ін.

32

Buluswar, Shashi Dhar. "Color-based models for outdoor machine vision." 2002. https://scholarworks.umass.edu/dissertations/AAI3039343.

Повний текст джерела

Анотація:

This study develops models for illumination and surface reflectance for use in outdoor color vision, and in particular for predicting the color of surfaces under outdoor conditions. Existing daylight and reflectance models that have been the basis for much of color research thus far have certain limitations that reduce their applicability to outdoor machine vision imagery. In that context, this work makes three specific contributions: (i) an explanation of why the current standard CIE daylight model cannot be used to predict the color of light incident on surfaces in machine vision images, (ii) a model (table) mapping the color of daylight to a broad range of sky conditions, and (iii) a simplified adaptation of the frequently used Dichromatic Reflectance Model for use with the developed daylight model. A series of experiments measure the accuracy of the daylight and reflectance models by predicting the colors of surfaces in real images. Finally, a series of tests demonstrate the potential use of these methods in outdoor applications such as road-following and obstacle detection.

Стилі APA, Harvard, Vancouver, ISO та ін.

33

Giuffrida, Laura Margarita. "Assessing the effect of weather on human outdoor perception using Twitter." Master's thesis, 2017. http://hdl.handle.net/10362/34460.

Повний текст джерела

Анотація:

Dissertation submitted in partial fulfilment of the requirements for the degree of Master of Science in Geospatial Technologies
Human Comfort in Outdoor Spaces (HCOS) is linked to physical, physiological and psychological responses of people to environmental variables. Previous studies have established comfort ranges for these variables through questionnaires, reaching only small populations. However, larger amounts of data could not only generate more robust results in local studies, but also allow the possibility of creating an approach that could be applied into a wider range of weather conditions and different climates. This thesis describes a new methodology to assess people’s perception of weather based on human responses to weather conditions extracted from tweets, with the purpose of establishing comfort ranges for environmental variables. Tweets containing weather-associated keywords were collected using the Twitter API and then linked to real-time meteorological data acquired from the Open Weather Map API, which provides weather variables measured nearby the locations in which the tweets were posted. Afterwards, people’s perception of weather was extracted from the tweets using a classifier trained specifically on weather data that identified irrelevant, neutral, positive and negative tweets. The obtained tweets and their related meteorological data were analyzed to establish comfort ranges. Comparing the resulting ranges to others obtained in previous studies, a generally good agreement was found with the indices Effective Temperature (ET) and Termohygrometric index (THI) derived from questionnaires, but the peak of comfort is shifted towards lower and higher temperatures, respectively. Regarding the single weather variables, the obtained comfort ranges are alike the ones found in previous research, in particular, the temperature comfort range matches perfectly at 20 °C – 22 °C. Therefore, it was concluded that tweets can be used for the assessment of HCOS; not only the results of this methodology are comparable to the ones obtained in previous studies, but also the procedure itself shows new features and opportunities for future applications.

Стилі APA, Harvard, Vancouver, ISO та ін.

34

Catchpole, Jason. "Adaptive vision based scene registration for outdoor augmentated reality." 2007. http://adt.waikato.ac.nz/public/adt-uow20081117.084239/index.html.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

35

Lin, Ze-Ming, and 林澤明. "Outdoor Road Classification Using Binocular Computer Vision Based onCounterpropagation Network." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/j3uj72.

Повний текст джерела

Анотація:

碩士
國立臺北科技大學
機電整合研究所
96
In the study, we propose the binocular computer vision based on counterpropagation network (CPN) to classify the road outdoors. First, we employ counterpropagation network using hue and saturation for road classification initially. Second, use 8-neighbors block voting method to improve result of CPN classification, but now the classified results only have similar local properties. Third, we calculate the height of feature points in the captured image. However, we first calibrate camera. We employ the linear least square method to obtain calibration parameters of the left and the right cameras using eight known 3D points and image points projected from real world into cameras. Then we can reconstruct the 3D information by using the calibration parameters and the image points of two cameras. In the stereo correspondence, we use Harris corner detector to extract the feature points of the left and the right image. These feature points are candidates using the fundamental matrix, epipolar geometry constraints, and template matching to look for the best corresponding points. After we know 3D information of corresponding points, we can understand whether classified results of CPN mistake or not. We combine result of CPN with 3D information of corresponding points. We can divide image into road and not road area. The result is helpful to ALV navigation.

Стилі APA, Harvard, Vancouver, ISO та ін.

36

Wu, Zong-Yuan, and 吳中遠. "Real-Time Vision-Assisted Outdoor Unmanned Vehicle System Design and Control." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/51511979214147808166.

Повний текст джерела

Анотація:

碩士
國立臺灣大學
應用力學研究所
94
The main theme of this thesis is to develop an integrated navigation and control system for an autonomous vehicle using Vision and DGPS in outdoor environments. The vehicle uses vision to detect landmarkers and DGPS information to determine the vehicle''s position. The vehicle is constructed step by step and the data exchange mechanism between sub-systems is set up through wireless network. The task of path following is performed such that the vehicle can track along a landmarker specified in advance. In the path following control problem, we use the Fuzzy control theory to determine the velocity of the vehicle. We use black-and-white landmarks in order to increase the contrast between the roads and the landmarks. The concept of template correlation is used to identify existing landmarkers in vision. The techniques of Edge Detention and Randomized Hough Transform are then applied to obtain the parameters of the landmarker. If no landmarker is detected by the vision system, the DGPS is used to control the vehicle approaching the specified position of the landmarkers. When the vehicle is passing a crossroad, we also use the GPS information to control the attitude of the vehicle toward the destination. Experimental results showed the effectiveness of our proposed navigation and control methodology.

Стилі APA, Harvard, Vancouver, ISO та ін.

37

Luo, Guan-Ming, and 駱冠銘. "The Vehicle-Vision-Based Moving-Object Detection System in All-Weather Situations." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/ngp49u.

Повний текст джерела

Анотація:

碩士
國立高雄應用科技大學
電子工程系碩士班
104
This paper proposed a moving object detection method for the vehicle vision based moving object detection system in all weather situations, which can effectively detect the moving objects shown in the image sequence. The detection system included three steps: (1) Image pre-processing: The users would be asked to set a region of interest (ROI). The ROI is set as the region to detect the moving objects. The upper half of region of image is detect daytime or nighttime and whether the car is moving or not. (2) Feature information detection: If image pre-processing has done, the system is divided daytime moving object detection and nighttime moving object detection, if the system judge that the weather is daytime state, the ROI would do road cutting, this method can filter left and right building and retain the lane information, then system use shadow feature to detect moving object, besides use HOG and SVM classifier to improve the detection accuracy. However in the left and right side moving object we can’t use shadow feature to detect moving object, therefore we use optical flow analysis, consider the optical flow length and direction to judge whether there are moving objects around on both sides; if the system judge that the weather is nighttime state, image’s RGB color space would convert to image’s HSV color space, then detect car light. (3) detection the moving objects: Use feature information to do morphological processing, noise filter and, intensify feature, finally do the bounding box for moving objects. Experimental results show this paper’s method can use vehicle camera to detect moving object in the urban roads. It’s Detection Rate has 80% in the day time; and has 60% in the night time. It’s False Detection Rate has less 5% in the daytime; and has less 15% in the night time, so the effect of showing the feasibility and value of this paper’s method.

Стилі APA, Harvard, Vancouver, ISO та ін.

38

劉明豐. "Outdoor autonomous vehicle navigation using stereo vision based on sensor-like points." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/10212944397516616639.

Повний текст джерела

Анотація:

碩士
國立臺北科技大學
機電整合研究所
90
Due to vast variability of the brightness in outdoor environment, the roads, trees, and lawns usually are not easy to recognize. In this study, we have developed a new navigating approach based on binocular stereovision that has successfully applied to an autonomous land vehicle (ALV) guidance and collision avoidance in outdoor environment. The study topics in the thesis include the information of road learning, stereo corresponding of the sensor-like points, collision avoidance and navigation. In a known outdoor environment, a learning approach to record the information of road before navigating is useful. The information of road includes hue, saturation and intensity (HSI) color feature distribution and the range of their color gradients. This approach will not be influenced by brightness easily, because the approach does not apply the intensity property. According to the learning information, we can label the pixel in the image whose H and S values are similar to the learned information as road. Furthermore, to reduce the cycle time, the image buffer is segmented into blocks of size . Stereo corresponding is a time-consuming task. If we perform corresponding on whole image, we can not navigate the ALV in real time. In the thesis, we propose an efficient and fast approach to sense five suitable points for corresponding, called sensor-like points approach. After sensing points, we suggest an improved approach to solve the stereo corresponding. The approach combines the advantages of feature-based matching and block matching to solve the optimal correspondence point. Using the corresponding point, we can reconstruct five 3-D points, and obtain five coordinates relative to ALV. Using those information we can navigate in the outdoor environment, and perform collision avoidance. The ALV system has been implemented, and it can be flexible to navigate in campus.

Стилі APA, Harvard, Vancouver, ISO та ін.

39

Carr, G. Peter K. "Enhancing surveillance video captured in inclement weather." Phd thesis, 2010. http://hdl.handle.net/1885/150329.

Повний текст джерела

Анотація:

This work describes a real-time video processing system for improving the visibility of images captured in inclement weather. The system is entirely automatic and is specifically tailored for use with regular surveillance cameras. Estimating what an image captured in fog would have looked like in good visibility conditions requires knowing the depth information of the scene. Since this information is unavailable, the system estimates the enhancement parameters by formulating a probability measure and using an optimization algorithm to find a set of highly probable parameter values. The thesis investigates current state of the art probability formulations and graph-cut based optimization algorithms. A more accurate probability model, which incorporates the expected geometry of a surveillance camera, is shown to be compatible with the a-expansion algorithm and is used to improve the result of the depth estimation process. A new formulation of a-expansion is presented, which means good solutions to convex functions of label difference can now be found efficiently. More importantly, the multilabel swap algorithm provides a flexible trade-off (in terms of solution quality and efficiency) over the range of current multilabel graph-cut algorithms (with the extremes being multilabel encodings and binary moves). Finally, the system implements a robust background estimation algorithm using the graphics processing unit to remove foreground objects from the image in real-time. Since foreground objects are the remaining dominant source of error in the estimation process, the resulting depth estimations induce few (if any) artifacts into the enhanced video.

Стилі APA, Harvard, Vancouver, ISO та ін.

40

Nathalie, El Nabbout. "Vehicle Tracking in Outdoor Environments using 3D Models." Thesis, 2008. http://hdl.handle.net/10012/3822.

Повний текст джерела

Анотація:

There has been a growth in demand for advancing algorithms in surveillance applications concerning moving vehicles where analysis of traffic has a potential application to security, traffic management (congestion and accident detection), speed measurement, car counting and statistics, as well as turning movement at intersections. This research focuses on multiple-vehicle detection, recognition, and tracking in urban environments based on video sequences obtained from a single CCD camera mounted on a pole at urban highways and crossroads. The proposed system integrates several modules including segmentation, object detection, object recognition and classification, and tracking. Background segmentation, based on Gaussian Mixture models, is used to extract moving objects from images using the respective foreground object information such as location, size, and color distribution. To recognize vehicles, a 3D polyhedral car model described by a set of parameters is built and mapped to the 2D edge information attained from the video sequence. The matching process is then used to classify the foreground object obtained into vehicles and non-vehicles. The output from the recognition model is used in tracking multiple cars based on a deterministic data association method that takes place between consecutive frame information. The multiple-vehicle surveillance system developed in this thesis, based on integrating different modules, provides a novel approach for vehicle monitoring. Furthermore, the system makes use of minimal a priori knowledge about vehicle location, size, type, numbers, and pathways. The system implemented in this work functions well under various camera perspectives, background clutter, vehicle viewpoints, road types, scale changes, image noise, image resolutions, and lighting conditions.

Стилі APA, Harvard, Vancouver, ISO та ін.

41

YEH, SHING-YU, and 葉星虞. "Using Deep Learning Approaches to Predict Indoor Thermal Comfort and Outdoor Rainfall Probability by Embedded Weather Box." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/zfyezh.

Повний текст джерела

Анотація:

碩士
逢甲大學
資訊工程學系
105
With new technological advancements, the mobile phones and 3C products have been popularized in the life. Internet of Things (IoT) is also equipped in our living space so that the internet can be anywhere and make our society more digitized. Face the pressure of work and the irritable things in life, people hope that they can have a more comfortable living space and so resulting in the applications for smart home appear quickly. For highly developed countries which faced aging societies, the health management of the elderly is one of the most important problems. The body of elderly is not only low resistance but also poor temperature regulation and sensitivity. Slight temperature changes may cause colds, fever and other diseases. Therefore, how to use a simple application to give people a thermal comfortable living space will be an important issue. Raining can not only affect thermal comfort but also cause inconvenience to people, e.g., shopping or hanging the clothes. If we can provide more accurate prediction of raining, people will be able to facilitate their planning schedules. This thesis aims to use the Arduino weather box to collect the weather data from the user’s living space, and then these data can be analyzed via Support Vector Machine (SVM) and Neural Network (NN) to predict thermal comfort and probability of rainfall. We compare the prediction accuracy of temperature and rainfall probability using the two machine learning approaches. We use accuracy and correlation coefficient to determine which one is the best. From the experimental results, we can find using NN can get better results of temperature prediction, and using SVM can get better results to predict rainfall probability.

Стилі APA, Harvard, Vancouver, ISO та ін.

42

Liao, Chiem-chun, and 廖建鈞. "Automatic Detection and Recognition of Traffic Signs in Outdoor Environment Using Machine Vision Techniques." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/23uv3d.

Повний текст джерела

Анотація:

碩士
國立臺灣科技大學
高分子系
94
This thesis applies image processing techniques to detect and recognize various colors and shapes of traffic signs. This information of road signs, provided to drivers in a computer-based vision system, is helpful for driving safety. In this study, the traffic sign detection and recognition system which is able to work well in complicated backgrounds and conditions is developed. We use HSV color model to reduce the disturbance of illumination and weather, and present a robust method to identify shapes of incomplete traffic signs. Two different color-pixel definitions are used for color detection and recognition, and calculation of gray-level variance, together with the Otsu statistical threshold selecting method, determines the black and white pixels. In order to increase recognition efficiency, we use the preliminary classification and cut part of the sign information. Furthermore, we divide traffic signs into three categories, which are graph signs, text signs and numeral signs, and they have their own recognition systems. In the experiment, 87 images include 102 traffic signs to discover 87 traffic signs based on detection system, which are used by the recognition system to identify accurately 77 traffic signs. The results demonstrate that the detection system can detect traffic signs under different weather conditions and slight cover conditions, and the recognition system has good performance.

Стилі APA, Harvard, Vancouver, ISO та ін.

43

Dai, Yu-Shu, and 戴玉書. "A Vision-based Vacant Parking Space Detection Framework for All-Day Outdoor Parking Lot Management." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/66287648969280737925.

Повний текст джерела

Анотація:

碩士
國立交通大學
電子研究所
100
In this thesis, we propose a vacant parking space detection system that works 24 hours a day. Especially, to capture images at night, we design a capture mode that takes images under different exposure settings and fuses these multi-exposure images into a clearer image. Besides, we combine a proposed Bayesian hierarchical framework (BHF) with the 3D-scene information by treating the whole parking lot as a structure consisting of plentiful surfaces. With the proposed framework, we extract feature vectors from each surface based on a modified version of the Histogram of Oriented Gradients (HOG) approach. By incorporating these feature vectors into specially designed probabilistic models, we can estimate the current parking status by finding the optimal statistical hypothesis among all possible status hypotheses. Experiments over real parking lot scenes have shown that our system can reliably detect vacant parking spaces day and night on an outdoor parking lot.

Стилі APA, Harvard, Vancouver, ISO та ін.

44

HSIEH, SHUO-PING, and 謝說評. "Comparison between Associations of Outdoor Air Pollutants and Weather Factors with Allergic Conjunctivitis and with Allergic Rhinitis in Taiwan." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/6z4g3j.

Повний текст джерела

Анотація:

碩士
慈濟大學
公共衛生學系碩士班
107
Background and Motivation: In the recent years, influences by industrialization and urbanization on air quality have been prevalent in Taiwan. The improvement on air pollutant emissions is limited, and the problem of air pollution has always existed. The increase in air pollutant concentration not only has an impact on the environment, but also has a bad impact on human health. Allergic conjunctivitis (AC) and allergic rhinitis (AR) are air pollution-related diseases that do affect each other. Most studies only focus on a single allergic condition, and rarely compare the similarities and differences between air pollutants and the two diseases further. Thus, the purpose of this study is to use diagnose of AC and AR from Taiwan’s National Health Insurance Research Database, to explore the relationship between the first incidence of first-time AC or AR and the exposure to air pollutants in Taiwan, and to further compare the relationships of the air pollutants with the two diseases. Methods: This study used one million samples of the Longitudinal National Health Insurance Database from 2004 to 2013. According to the 9th version of the international disease classification (ICD-9-CM), the study selected patients diagnosed with AC or AR, and linked them with the air quality monitoring data by Environmental Protection Administration as exposure data. The case-crossover design was used for this case control study. The study used the conditional logistic regression model to estimate the relationship between air pollutant concentrations, AC and AR. In addition, considering the lag effect of allergic reactions possibly tiggered by air pollutants, the concentrations of air pollutants on the day (Lag0) and 1 and 2 previous days (Lag-1, Lag-2) were included and stratified by sex, age and season. The comparison between the two air pollutant-disease (AC or AR) relationships was conducte by the logistic regression model. Results: There were 100,636 patients with first occurrence of AC during 2004-2013, with an average age of 27.6 years. The first occurrences of AC were significantly the most for 19-49 years by age (38.43%), for women by sex (56.23%), and in spring by season (29.63%). There were 140,365 patients with first occurrence of AR during 2004-2013, with an average age of 31.41 years. The first occurrences of AR were significantly the most for 19-49 years by age (44.67%), for women by sex (53.36%), and in winter by season (28.65%). Multivariate conditional logistic regression analyses indicated that ozone (O3), nitrogen dioxide (NO2) and temperature were positively associated with AC (P < 0.001), while relative humidity was negatively related to AC (P < 0.001). For analysis of AR, carbon monoxide (CO)　and 　nitrogen dioxide (NO2) were positively associated (P < 0.001), while temperature and relative humidity was negatively related (P < 0.001).We used multivariate logistic regression analysis to compare the two air pollutant-disease relationships, after adjustment for basic demographics (gender, age), season O3, RH and temperature. Compared with AC, AR was found to be associated with the lower NO2 (Model 4: OR=0.990). Conclusions: AC and AR are often considered to be comorbid, and related to weather changes, albeit with different trends related to temperature. They are both associated with air pollution NO2, presumably the main source to be traffic emissions. Comparing the relations of NO2 with the two diseases, we found that AR is associated with the lower NO2 concentration, which may slightly explain more patients with AR than with AC.

Стилі APA, Harvard, Vancouver, ISO та ін.

45

Lai, Chih-Chiun, and 賴志群. "Outdoor Autonomous Land Vehicle Guidance by Road Information Using Computer Vision and Fuzzy Wheel Adjustment Techniques." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/11862535598705120996.

Повний текст джерела

Анотація:

碩士
國立交通大學
資訊科學研究所
81
An approach to the guidance of autonotnous land vehicles (ALV's) for outdoor navigation by road information using comater vision and fuzzy wheel adjustment techniques is proposed. Several types of landmarks or features on roads, such as different kinds of path lines and lampposts, are usilized for vision-based navigation. Lamppost positions and road conditions are extracted as the model information for navigation guidance. Using a line following method, the ALV can be guided on roads with path lines on them. By model information, the time that lampposts appear in the image can be predicted. The edges of lampposts are extracted to locate the ALV correctly and quickly. A dynamic image thresholding method is used in real time to solve the problem caused by the sunlight change A modified least square-error line approximation method is employed to extract path lines. Fuzzy set theory is applied to determine the turn angle for wheel adjustment. In addition, a speed adjustment approach is used to keep the ALV at stable speeds on fluctuating roads. Lots of successful navigation experiments using a real ALV confirm the effectiveness of the proposed methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

46

Chen, Kuang-Hsiung, and 陳光雄. "Vision-based Autonomous Land Vehicle Guidance in Outdoor Road Environments Using Feature Clustering and Shape Matching Techniques." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/42415586063050695099.

Повний текст джерела

Анотація:

博士
國立交通大學
資訊科學系
87
Autonomous land vehicles (ALV''s) are useful for many automation applications in both indoor and outdoor environments. Successful ALV navigation requires integration of techniques of environment sensing and learning, image processing and feature extraction, ALV location, path planning, wheel control, and so on. In outdoor environments, because of the great variety of object and road conditions like irregular and unstable features on objects, moving objects, shadows, degraded regions, curved roads, ascending or descending roads, changes of illumination, and even rain, we need to combine different problem-solving algorithms and perhaps equip multiple sensors to solve the complex problem of ALV guidance in roads. In this dissertation, five approaches to vision-based ALV guidance in outdoor road environments are proposed. The conventional ways of ALV guidance, which are generally complex and time-consuming, are avoided in the proposed approaches; instead, efficient and effective ways of ALV guidance, which are usually easier and faster, are adopted. In the first approach, color information clustering and combined line and road following techniques are used for ALV guidance on straight roads with constant widths. The clustering algorithm is used to solve the problem caused by great changes of intensity in navigation. The combined line and road following technique is used to achieve faster and more flexible navigations. To locate the ALV for line following or road following, the line-model or road-model, which are constructed using path lines or road boundaries, are matched with the extracted path lines or road surface in the image, respectively. In the second approach, three tangent lines, that are extracted from the dotted central path line and collected from the images of the previous and current cycles, are used to judge whether the ALV is leaving a straight road and entering a curved road in the current cycle. When the ALV enters a curved road, the three tangent lines collected so far are used again to derive the navigation path at a curved turning road section. The navigation path is assumed to be a circle and is re-derived cyclically for safe navigation. Moreover, the three tangent lines can also be used to judge whether the ALV is leaving a curved road and entering a straight road. The third approach allows variations of road widths, which are caused by existence of static cars on the roadside or moving cars on the road lane. The conventional way of detecting obstacles and cars in the navigation route, which is in general complex and inefficient, is avoided; instead, collision-free road area detecting, which is usually easier and faster, is adopted. Road boundaries are used to construct the reference model, and the road surface intensity is selected as the visual feature in this approach. The reference model is then matched with the extracted road surface in the image to find the safe road area and the ALV location on the safe road area. In the fourth approach, image sequence and coordination transformation techniques are used to detect obstacles ahead on the safe road area in navigation. To judge whether one object newly appearing in the image of the current cycle is an obstacle, the object boundary shape is first extracted from the image. After the translation vector from the ALV location in the current cycle to that in the next cycle is estimated, the position of the boundary shape in the image of the next cycle is predicted using coordinate transformation techniques. The predicted boundary shape is then matched with the extracted boundary shape of the object in the image of the next cycle to judge whether the object is an obstacle. In the fifth approach, the ALV can keep driving forward even when ascending or descending roads appear ahead of the ALV. When the ALV keeps driving on a flat road, it detects and follows the flat road. When the ALV navigates at a transition from a flat road into an ascending road, both of the flat and the ascending road boundaries are extracted from the image, which are then used to estimate the slant angle of the ascending road and compute accordingly the connection points of the flat and the ascending road boundaries. When the ALV drives on the flat road but the flat road boundaries disappear from the image, the flat road boundaries are derived using the estimated slant angle, the stable features of the ascending road boundaries in the image, and the predicted connection points of the ascending and the flat road boundaries. The ALV then follows the derived flat road because it still drives on the flat road. At the beginning of subsequent each navigation cycle, the ALV predicts the flat road boundaries in the image using the derived flat road boundaries just described in the previous cycle. The predicted flat road boundaries are then matched with the extracted ascending road boundaries in the image to judge whether the ALV has entered the ascending road in the current cycle. This way of guidance is also used when the ALV navigates at a transition from a flat road into a descending road. A lot of successful navigation tests show that the proposed approaches are effective for ALV guidance in outdoor road environments.

Стилі APA, Harvard, Vancouver, ISO та ін.

47

Chen, Yung-Der, and 陳永德. "A Study on Outdoor Guidance of Autonomous Land Vehicles by Computer Vision Based on Improved A* Search." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/59f66e.

Повний текст джерела

Анотація:

碩士
國立臺北科技大學
電腦與通訊研究所
95
In this paper, we develop the system of autonomous land vehicles (ALV) by computer vision based on artificial intelligent (AI) policy. It makes ALV adapted to the complex environment. This system uses two cameras to capture two images from the front of the vehicle and calculate the 3D information of environment. Though the obtained 3D information, we can recognize region of road and region of obstacle in front of the vehicle. Using navigation policy based on AI to make vehicle navigate in outdoor environment. In path planning, combining ant colony optimization (ACO) and search program the best path. First, we obtain the navigation map of the front of the vehicle from charge-coupled device (CCD). After path planning of ACO, we can get a kind of novel trail information (pheromone). Using trail information improves the parameters of search to get novel estimation of node. According to estimation of nodes on searching path, we obtain a path from origin to target. After obtaining road information, the path of navigation is searched by E-compass and improved search. We make ALV avoid the obstacle safely and run toward the goal in an appropriate path. The ALV system has been performed in the outdoor to demonstrate the effectiveness of the presented method.

Стилі APA, Harvard, Vancouver, ISO та ін.

48

chang, yu-ching, and 張煜青. "A Study on Outdoor Guidance of Autonomous Land Vehicles by Binocular Computer Vision Based on Artificial Intelligent Policy." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/84844257100244703271.

Повний текст джерела

Анотація:

碩士
國立臺北科技大學
自動化科技研究所
91
In this thesis, we have developed a new outdoor guidance system of autonomous land vehicle (ALV) equipped with binocular stereovision system based on artificial intelligence (AI) policy. The system uses two cameras to reconstruct the 3D structure of the scene. We can utilize the 3D information of the scene to recognize all obstacles. Hence, The ALV can perform navigation and obstacle avoidance in the outdoor environment using AI policy. The study topics in the thesis include camera calibration, stereo corresponding, improve information of the scene, obstacle avoidance and navigation based on AI policy. The correspondence problem is the important and most difficult problem of stereovision. The accuracy of 3D scene information will be affected greatly by the correspondence. In the study, first, we present a fast and simple approach to select reference points from the left image. The approach combines edge of the scene and several sensory vertical lines to select reference points. Then, we present a two-layer hierarchical stereo correspondence to the right image in binocular stereovision. A low-level processing is employed to obtain a set of points that are candidates for correspondence using Grey relation approach (GRA). The refinement of the set of low-level correspondences is performed by a high-level correspondence process. The high-level processing uses a permutation of genetic algorithm (GAP) approach for searching optimal solution from the solution space. Some constraints is embedded in the fitness function. The methods have been tested on a series of real images and perform very well. After the calibrated parameters and correspondence pairs are obtained, the 3D information of the scene can be computed by linear least-square method. But there are also several departures result from correspondence. We employ the nearest neighbor decision rules (NNDR) approach to solve this problem. Hence, we can obtain correct information of the scene via the approach on whole images. After we derive the 3D structure of the scene, we can know where the obstacles are. Hence, we propose navigation policy based on AI approach. The approach adopts a simple reactive navigation strategy by combining repulsion from obstacles with attraction to a goal. That is locally optimal in the sense of minimizing the hitting probability based on what is currently known about the world. Therefore, we can find an appropriate path for the ALV navigation. The ALV system has been performed in campus to demonstrate the effectiveness of the presented method.

Стилі APA, Harvard, Vancouver, ISO та ін.

49

ZHU, ZE-HONG, and 朱澤宏. "Autonomous land vehicle guidance by computer vision aechniquse using path line and road lamppost information for outdoor navigation." Thesis, 1992. http://ndltd.ncl.edu.tw/handle/89369183714029878642.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

50

Tang, Hsin-Jun, and 唐心駿. "In-car Tour Guidance in Outdoor Parks Using Augmented Reality and Omni-vision Techniques with an Automatic Learning Capability." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/71962519957595476371.

Повний текст джерела

Анотація:

碩士
國立交通大學
資訊科學與工程研究所
102
In this study, an augmented-reality based in-car tour guidance system with an automatic learning capability for use in outdoor park areas using computer vision techniques has been proposed. With the proposed system, a user can construct a tour guidance map for a park area in a simple and clear way, and use this map to provide tour guidance information to in-car passengers. When a passenger is in a vehicle driven in a park area, he/she can get from the system tour guidance information mainly about the names of the nearby buildings appearing along the way on the guidance path. The building names are augmented on the passenger-view image which is displayed on the mobile device held by the passenger. To implement the proposed system with the above-mentioned capability, at first an environment map is generated in the learning phase, which includes the information about the tour path and the along-path buildings (mainly the building names). All the data are learned either manually or by programs, and saved into the database for use in the navigation phase. Secondly, a method for automatic learning of the along-path vertical-line features, mainly, the edges of light poles, is proposed for use by the system. In this feature-learning stage, the vehicle equipped with a GPS device and a two-camera omni-imaging device is driven on a pre-selected guidance path. On each visited spot of the path, the system analyzes the input omni-image pair taken by the upper and lower cameras of the imaging device respectively, to detect the nearby vertical-line features and compute the positions and heights of them by the use of the GPS device. And the learned features are added to the map as landmarks for vehicle localization in the navigation phase. Next, a method for vehicle localization is proposed for use by the system. The method analyzes the omni-image taken by the upper camera of the imaging device to detect the learned features by the use of the learned information about them and the GPS device. It then computes the vehicle position by using the relation between the features and the vehicle. Finally, a method for AR-based guidance is proposed, which at first generates a passenger-view image by transforming the omni-image acquired from the upper omni-camera onto the user’s mobile-device screen. The method then uses the passenger-view image as a base, and augments the building names on the image before the image is displayed. To accomplish this function, the system computes the position of each building on the passenger-view image by using the result of vehicle localization. Good experimental results are also presented to show the feasibility of the proposed methods for real applications.

Стилі APA, Harvard, Vancouver, ISO та ін.

Дисертації з теми "Outdoor vision and weather"

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями