Thèses sur le sujet « Automatic Motion Detection and Analysis »
Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Automatic Motion Detection and Analysis.
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleures thèses pour votre recherche sur le sujet « Automatic Motion Detection and Analysis ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
1
Richards, Mark Andrew. « An intuitive motion-based input model for mobile devices ». Queensland University of Technology, 2006. http://eprints.qut.edu.au/16556/.
Texte intégralRésumé :
Traditional methods of input on mobile devices are cumbersome and difficult to use. Devices have become smaller, while their operating systems have become more complex, to the extent that they are approaching the level of functionality found on desktop computer operating systems. The buttons and toggle-sticks currently employed by mobile devices are a relatively poor replacement for the keyboard and mouse style user interfaces used on their desktop computer counterparts. For example, when looking at a screen image on a device, we should be able to move the device to the left to indicate we wish the image to be panned in the same direction.
This research investigates a new input model based on the natural hand motions and reactions of users. The model developed by this work uses the generic embedded video cameras available on almost all current-generation mobile devices to determine how the device is being moved and maps this movement to an appropriate action.
Surveys using mobile devices were undertaken to determine both the appropriateness and efficacy of such a model as well as to collect the foundational data with which to build the model. Direct mappings between motions and inputs were achieved by analysing users' motions and reactions in response to different tasks.
Upon the framework being completed, a proof of concept was created upon the Windows Mobile Platform. This proof of concept leverages both DirectShow and Direct3D to track objects in the video stream, maps these objects to a three-dimensional plane, and determines device movements from this data.
This input model holds the promise of being a simpler and more intuitive method for users to interact with their mobile devices, and has the added advantage that no hardware additions or modifications are required the existing mobile devices.
2
Richards, Mark Andrew. « An intuitive motion-based input model for mobile devices ». Thesis, Queensland University of Technology, 2006. https://eprints.qut.edu.au/16556/1/Mark_Richards_Thesis.pdf.
Texte intégralRésumé :
Traditional methods of input on mobile devices are cumbersome and difficult to use. Devices have become smaller, while their operating systems have become more complex, to the extent that they are approaching the level of functionality found on desktop computer operating systems. The buttons and toggle-sticks currently employed by mobile devices are a relatively poor replacement for the keyboard and mouse style user interfaces used on their desktop computer counterparts. For example, when looking at a screen image on a device, we should be able to move the device to the left to indicate we wish the image to be panned in the same direction.
This research investigates a new input model based on the natural hand motions and reactions of users. The model developed by this work uses the generic embedded video cameras available on almost all current-generation mobile devices to determine how the device is being moved and maps this movement to an appropriate action.
Surveys using mobile devices were undertaken to determine both the appropriateness and efficacy of such a model as well as to collect the foundational data with which to build the model. Direct mappings between motions and inputs were achieved by analysing users' motions and reactions in response to different tasks.
Upon the framework being completed, a proof of concept was created upon the Windows Mobile Platform. This proof of concept leverages both DirectShow and Direct3D to track objects in the video stream, maps these objects to a three-dimensional plane, and determines device movements from this data.
This input model holds the promise of being a simpler and more intuitive method for users to interact with their mobile devices, and has the added advantage that no hardware additions or modifications are required the existing mobile devices.
3
Brulin, Mathieu. « Analyse sémantique d'un trafic routier dans un contexte de vidéo-surveillance ». Thesis, Bordeaux 1, 2012. http://www.theses.fr/2012BOR14589/document.
Texte intégralRésumé :
Les problématiques de sécurité, ainsi que le coût de moins en moins élevé des caméras numériques, amènent aujourd'hui à un développement rapide des systèmes de vidéosurveillance. Devant le nombre croissant de caméras et l'impossibilité de placer un opérateur humain devant chacune d'elles, il est nécessaire de mettre en oeuvre des outils d'analyse capables d'identifier des évènements spécifiques. Le travail présenté dans cette thèse s'inscrit dans le cadre d'une collaboration entre le Laboratoire Bordelais de Recherche en Informatique (LaBRI) et la société Adacis. L'objectif consiste à concevoir un système complet de vidéo-surveillance destiné à l'analyse automatique de scènes autoroutières et la détection d'incidents. Le système doit être autonome, le moins supervisé possible et doit fournir une détection en temps réel d'un évènement.Pour parvenir à cet objectif, l'approche utilisée se décompose en plusieurs étapes. Une étape d'analyse de bas-niveau, telle que l'estimation et la détection des régions en mouvement, une identification des caractéristiques d'un niveau sémantique plus élevé, telles que l'extraction des objets et la trajectoire des objets, et l'identification d'évènements ou de comportements particuliers, tel que le non respect des règles de sécurité. Les techniques employées s'appuient sur des modèles statistiques permettant de prendre en compte les incertitudes sur les mesures et observations (bruits d'acquisition, données manquantes, ...).Ainsi, la détection des régions en mouvement s'effectue au travers la modélisation de la couleur de l'arrière-plan. Le modèle statistique utilisé est un modèle de mélange de lois, permettant de caractériser la multi-modalité des valeurs prises par les pixels. L'estimation du flot optique, de la différence de gradient et la détection d'ombres et de reflets sont employées pour confirmer ou infirmer le résultat de la segmentation.L'étape de suivi repose sur un filtrage prédictif basé sur un modèle de mouvement à vitesse constante. Le cas particulier du filtrage de Kalman (filtrage tout gaussien) est employé, permettant de fournir une estimation a priori de la position des objets en se basant sur le modèle de mouvement prédéfini.L'étape d'analyse de comportement est constituée de deux approches : la première consiste à exploiter les informations obtenues dans les étapes précédentes de l'analyse. Autrement dit, il s'agit d'extraire et d'analyser chaque objet afin d'en étudier son comportement. La seconde étape consiste à détecter les évènements à travers une coupe du volume 2d+t de la vidéo. Les cartes spatio-temporelles obtenues sont utilisées pour estimer les statistiques du trafic, ainsi que pour détecter des évènements telles que l'arrêt des véhicules.Pour aider à la segmentation et au suivi des objets, un modèle de la structure de la scène et de ses caractéristiques est proposé. Ce modèle est construit à l'aide d'une étape d'apprentissage durant laquelle aucune intervention de l'utilisateur n'est requise. La construction du modèle s'effectue à travers l'analyse d'une séquence d'entraînement durant laquelle les contours de l'arrière-plan et les trajectoires typiques des véhicules sont estimés. Ces informations sont ensuite combinées pour fournit une estimation du point de fuite, les délimitations des voies de circulation et une approximation des lignes de profondeur dans l'image. En parallèle, un modèle statistique du sens de direction du trafic est proposé. La modélisation de données orientées nécessite l'utilisation de lois de distributions particulières, due à la nature périodique de la donnée. Un mélange de lois de type von-Mises est utilisée pour caractériser le sens de direction du traficAutomatic traffic monitoring plays an important role in traffic surveillance. Video cameras are relatively inexpensive surveillance tools, but necessitate robust, efficient and automated video analysis algorithms. The loss of information caused by the formation of images under perspective projection made the automatic task of detection and tracking vehicles a very challenging problem, but essential to extract a semantic interpretation of vehicles behaviors. The work proposed in this thesis comes from a collaboration between the LaBRI (Laboratoire Bordelais de Recherche en Informatique) and the company Adacis. The aim is to elaborate a complete video-surveillance system designed for automatic incident detection.To reach this objective, traffic scene analysis proceeds from low-level processing to high-level descriptions of the traffic, which can be in a wide variety of type: vehicles entering or exiting the scene, vehicles collisions, vehicles' speed that are too fast or too low, stopped vehicles or objects obstructing part of the road... A large number of road traffic monitoring systems are based on background subtraction techniques to segment the regions of interest of the image. Resulted regions are then tracked and trajectories are used to extract a semantic interpretation of the vehicles behaviors.The motion detection is based on a statistical model of background color. The model used is a mixture model of probabilistic laws, which allows to characterize multimodal distributions for each pixel. Estimation of optical flow, a gradient difference estimation and shadow and highlight detection are used to confirm or invalidate the segmentation results.The tracking process is based on a predictive filter using a motion model with constant velocity. A simple Kalman filter is employed, which allow to predict state of objets based on a \textit{a priori} information from the motion model.The behavior analysis step contains two approaches : the first one consists in exploiting information from low-level and mid-level analysis. Objects and their trajectories are analysed and used to extract abnormal behavior. The second approach consists in analysing a spatio-temporal slice in the 3D video volume. The extracted maps are used to estimate statistics about traffic and are used to detect abnormal behavior such as stopped vehicules or wrong way drivers.In order to help the segmentaion and the tracking processes, a structure model of the scene is proposed. This model is constructed using an unsupervised learning step. During this learning step, gradient information from the background image and typical trajectories of vehicles are estimated. The results are combined to estimate the vanishing point of the scene, the lanes boundaries and a rough depth estimation is performed. In parallel, a statistical model of the trafic flow direction is proposed. To deal with periodic data, a von-Mises mixture model is used to characterize the traffic flow direction
4
Mawla, Aya Abdul. « Real time automatic intruder detection system (RAIDS) ». Thesis, University of Bristol, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.319332.
Texte intégral
5
Hayfron-Acquah, James Ben. « Automatic gait recognition by symmetry analysis ». Thesis, University of Southampton, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.274080.
Texte intégral
6
Case, Isaac. « Automatic object detection and tracking in video / ». Online version of thesis, 2010. http://hdl.handle.net/1850/12332.
Texte intégral
7
Aleixo, de Matos SeÌrgio Guilherme. « Automatic detection and analysis of cough sounds ». Thesis, University of Leicester, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.437913.
Texte intégral
8
Shankaranarayanan, S. « Detection of Coreferences in Automatic Specifications Analysis ». Thesis, Virginia Tech, 1994. http://hdl.handle.net/10919/42360.
Texte intégralRésumé :
Specifications on digital hardware systems typically contain descriptions and requirements expressed in natural language and diagrams of various types. The objective of the research reported here is the automatic detection of common references ("coreferences") to objects in natural language specification statements in order to permit automatic integration of requirements. This thesis describes a prototype system for detecting coreferences. First, the natural language statements are translated into conceptual graphs (semantic nets). Then, these graphs are scanned by a rule-based system to determine whether each concept that is encountered is the definition of a new concept or a reference to a previously defined concept. Tests performed on the system developed indicate a high percentage rate of correct classifications.Master of Science
9
Li, Yunming. « Machine vision algorithms for mining equipment automation ». Thesis, Queensland University of Technology, 2000.
Trouver le texte intégral
10
Liu, Chang. « Human motion detection and action recognition ». HKBU Institutional Repository, 2010. http://repository.hkbu.edu.hk/etd_ra/1108.
Texte intégral
11
Santos, Paulo Alexandre Vieira Jacinto dos. « Automatic detection of user transitionality by analysis of interaction ». Diss., Georgia Institute of Technology, 1995. http://hdl.handle.net/1853/9154.
Texte intégral
12
Turabzadeh, Saeed. « Automatic emotional state detection and analysis on embedded devices ». Thesis, Brunel University, 2015. http://bura.brunel.ac.uk/handle/2438/12072.
Texte intégralRésumé :
From the last decade, studies on human facial emotion recognition revealed that computing models based on regression modelling can produce applicable performance. In this study, an automatic facial expression real-time system was built and tested. The method is used in this study has been used widely in different areas such as Local Binary Pattern method, which has been used in many research projects in machine vision, and the K-Nearest Neighbour algorithm is method utilized for regression modelling. In this study, these two techniques has been used and implemented on the FPGA for the first time, on the side and joined together to great the model in such way to display a continues and automatic emotional state detection model on the monitor. To evaluate the effectiveness of the classifier technique for human emotion recognition from video, the model was designed and tested on MATLAB environment and then MATLAB Simulink environment that is capable of recognizing continuous facial expression in real time with a rate of 1 frame per second and implemented on a desktop PC. It has been evaluated in a testing dataset and the experimental results were promising with the accuracy of 51.28%. The datasets and labels used in this study are made from videos which, recorded twice from 5 participants while watching a video. In order to implement it in real-time in faster frame rate, the facial expression recognition system was built on FPGA. The model was built on Atlys™ Spartan-6 FPGA Development Board. It can perform continuously emotional state recognition in real time at a frame rate of 30 with the accuracy of 47.44%. A graphic user interface was designed to display the participant video in real time and also two dimensional predict labels of the emotion at the same time. This is the first time that automatic emotional state detection has been successfully implemented on FPGA by using LBP and K-NN techniques in such way to display a continues and automatic emotional state detection model on the monitor.
13
Ullah, Habib. « Crowd Motion Analysis : Segmentation, Anomaly Detection, and Behavior Classification ». Doctoral thesis, Università degli studi di Trento, 2015. https://hdl.handle.net/11572/369001.
Texte intégralRésumé :
The objective of this doctoral study is to develop efficient techniques for flow segmentation, anomaly detection, and behavior classification in crowd scenes. Considering the complexities of occlusion, we focused our study on gathering the motion information at a higher scale, thus not associating it to single objects, but considering the crowd as a single entity. Firstly,we propose methods for flow segmentation based on correlation features, graph cut, Conditional Random Fields (CRF), enthalpy model, and particle mutual influence model. Secondly, methods based on deviant orientation information, Gaussian Mixture Model (GMM), and MLP neural network combined with GoodFeaturesToTrack are proposed to detect two types of anomalies. The first one detects deviant motion of the pedestrians compared to what has been observed beforehand. The second one detects panic situation by adopting the GMM and MLP to learn the behavior of the motion features extracted from a grid of particles and GoodFeaturesToTrack, respectively. Finally, we propose particle-driven and hybrid appraoches to classify the behaviors of crowd in terms of lane, arch/ring, bottleneck, blocking and fountainhead within a region of interest (ROI). For this purpose, the particle-driven approach extracts and fuses spatio-temporal features together. The spatial features represent the density of neighboring particles in the predefined proximity, whereas the temporal features represent the rendering of trajectories traveled by the particles. The hybrid approach exploits a thermal diffusion process combined with an extended variant of the social force model (SFM).
14
Ullah, Habib. « Crowd Motion Analysis : Segmentation, Anomaly Detection, and Behavior Classification ». Doctoral thesis, University of Trento, 2015. http://eprints-phd.biblio.unitn.it/1406/1/PhD_Thesis_Habib.pdf.
Texte intégralRésumé :
The objective of this doctoral study is to develop efficient techniques for flow segmentation, anomaly detection, and behavior classification in crowd scenes. Considering the complexities of occlusion, we focused our study on gathering the motion information at a higher scale, thus not associating it to single objects, but considering the crowd as a single entity. Firstly,we propose methods for flow segmentation based on correlation features, graph cut, Conditional Random Fields (CRF), enthalpy model, and particle mutual influence model. Secondly, methods based on deviant orientation information, Gaussian Mixture Model (GMM), and MLP neural network combined with GoodFeaturesToTrack are proposed to detect two types of anomalies. The first one detects deviant motion of the pedestrians compared to what has been observed beforehand. The second one detects panic situation by adopting the GMM and MLP to learn the behavior of the motion features extracted from a grid of particles and GoodFeaturesToTrack, respectively. Finally, we propose particle-driven and hybrid appraoches to classify the behaviors of crowd in terms of lane, arch/ring, bottleneck, blocking and fountainhead within a region of interest (ROI). For this purpose, the particle-driven approach extracts and fuses spatio-temporal features together. The spatial features represent the density of neighboring particles in the predefined proximity, whereas the temporal features represent the rendering of trajectories traveled by the particles. The hybrid approach exploits a thermal diffusion process combined with an extended variant of the social force model (SFM).
15
Ye, Ming. « Robust visual motion analysis : piecewise-smooth optical flow and motion-based detection and tracking / ». Thesis, Connect to this title online ; UW restricted, 2002. http://hdl.handle.net/1773/6077.
Texte intégral
16
Pruthi, Tarun. « Analysis, vocal-tract modeling, and automatic detection of vowel nasalization ». College Park, Md. : University of Maryland, 2007. http://hdl.handle.net/1903/4273.
Texte intégralRésumé :
Thesis (Ph. D.) -- University of Maryland, College Park, 2007.Thesis research directed by: Electrical Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
17
Simonin, David. « Automatic detection and analysis of internal waves on SAR images ». Thesis, University of Southampton, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.420213.
Texte intégral
18
Forsberg, Viktor. « AUTOMATIC ANOMALY DETECTION AND ROOT CAUSE ANALYSIS FOR MICROSERVICE CLUSTERS ». Thesis, Umeå universitet, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-164740.
Texte intégralRésumé :
Large microservice clusters deployed in the cloud can be very difficult to both monitor and debug. Monitoring theses clusters is a first step towards detection of anomalies, deviations from normal behaviour. Anomalies are often indicators that a component is failing or is about to fail and should hence be detected as soon as possible. There are often lots of metrics available to view. Furthermore, any errors that occur often propagate to other microservices making it hard to manually locate the root cause of an anomaly, because of this automatic methods are needed to detect and correct the problems. The goal of this thesis is to create a solution that can automatically monitor a microservice cluster, detect anomalies, and find a root cause. The anomaly detection is based on an unsupervised clustering algorithm that learns the normal behaviour of each service and then look for data that falls outside that behaviour. Once an anomaly is detected the proposed method tries to match the data against predefined root causes. The proposed solution is evaluated in a real microservice cluster deployed in the cloud, using Kubernetes together with a service mesh and several other tools to help gather metrics and trace requests in the system.
19
Zhou, Huiyu. « Efficient ego-motion tracking and obstacle detection using gait analysis ». Thesis, Heriot-Watt University, 2006. http://hdl.handle.net/10399/141.
Texte intégral
20
He, Shu. « Facial motion analysis for facial paralysis assessment and lie detection ». Thesis, University of Strathclyde, 2009. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.501886.
Texte intégral
21
Lumbreras, Alberto. « Automatic role detection in online forums ». Thesis, Lyon, 2016. http://www.theses.fr/2016LYSE2111/document.
Texte intégralRésumé :
Nous traitons dans cette thèse le problème de la détection des rôles des utilisateurs sur des forums de discussion en ligne. On peut détenir un rôle comme l'ensemble des comportements propres d'une personne ou d'une position. Sur les forums de discussion, les comportements sont surtout observés à travers des conversations. Pour autant, nous centrons notre attention sur la manière dont les utilisateurs dialoguent. Nous proposons trois méthodes pour détecter des groupes d'utilisateurs où les utilisateurs d'un même groupe dialoguent de façon similaire.Notre première méthode se base sur les structures des conversations dans lesquelles les utilisateurs participent. Nous appliquons des notions de voisinage différentes (radiusbased, order-based, and time-based) applicables aux commentaires qui sont représentés par des noeuds sur un arbre. Nous comparons les motifs de conversation qu'ils permettent de détecter ainsi que les groupes d'utilisateurs associés à des motifs similaires. Notre deuxième méthode se base sur des modèles stochastiques de croissance appliqués aux fils de discussion. Nous proposons une méthode pour trouver des groupes d'utilisateurs qui ont tendance à répondre au même type de commentaire. Nous montrons que, bien qu'il y ait des groupes d'utilisateurs avec des motifs de réponse similaires, il n'y a pas d'évidence forte qui confirme que ces comportements présentent des propriétés prédictives quant aux comportements futurs {sauf pour quelques groupes avec des comportements extrêmes. Avec notre troisième méthode nous intégrons les types de données utilisés dans les deux méthodes précédentes (feature-based et behavioral ou functional-based) et nous montrons que le modèle trouve des groupes en ayant besoin de moins d'observations. L'hypothèse du modèle est que les utilisateurs qui ont des caractéristiques similaires ont aussi des comportements similairesThis thesis addresses the problem of detecting user roles in online discussion forums. A role may be defined as the set of behaviors characteristic of a person or a position. In discussion forums, behaviors are primarily observed through conversations. Hence, we focus our attention on how users discuss. We propose three methods to detect groups of users with similar conversational behaviors.Our first method for the detection of roles is based on conversational structures. Weapply different notions of neighborhood for posts in tree graphs (radius-based, order-based, and time-based) and compare the conversational patterns that they detect as well as the clusters of users with similar conversational patterns.Our second method is based on stochastic models of growth for conversation threads.Building upon these models we propose a method to find groups of users that tend to reply to the same type of posts. We show that, while there are clusters of users with similar replying patterns, there is no strong evidence that these behaviors are predictive of future behaviors |except for some groups of users with extreme behaviors.In out last method, we integrate the type of data used in the two previous methods(feature-based and behavioral or functional-based) and show that we can find clusters using fewer examples. The model exploits the idea that users with similar features have similar behaviors
22
Partsinevelos, Panayotis. « Detection and Generalization of Spatio-temporal Trajectories for Motion Imagery ». Fogler Library, University of Maine, 2002. http://www.library.umaine.edu/theses/pdf/PartsinevelosP2002.pdf.
Texte intégral
23
Syal, Astha. « Automatic Network Traffic Anomaly Detection and Analysis using SupervisedMachine Learning Techniques ». Youngstown State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1578259840945109.
Texte intégral
24
Bodnarova, Adriana. « Texture analysis for automatic visual inspection and flaw detection in textiles ». Thesis, Queensland University of Technology, 2000.
Trouver le texte intégral
25
Rabe, Clemens [Verfasser]. « Detection of Moving Objects by Spatio-Temporal Motion Analysis / Clemens Rabe ». Kiel : Universitätsbibliothek Kiel, 2011. http://d-nb.info/1020202637/34.
Texte intégral
26
Zhu, Winstead Xingran. « Hotspot Detection for Automatic Podcast Trailer Generation ». Thesis, Uppsala universitet, Institutionen för lingvistik och filologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-444887.
Texte intégralRésumé :
With podcasts being a fast growing audio-only form of media, an effective way of promoting different podcast shows becomes more and more vital to all the stakeholders concerned, including the podcast creators, the podcast streaming platforms, and the podcast listeners. This thesis investigates the relatively little studied topic of automatic podcast trailer generation, with the purpose of en- hancing the overall visibility and publicity of different podcast contents and gen- erating more user engagement in podcast listening. This thesis takes a hotspot- based approach, by specifically defining the vague concept of “hotspot” and designing different appropriate methods for hotspot detection. Different meth- ods are analyzed and compared, and the best methods are selected. The selected methods are then used to construct an automatic podcast trailer generation sys- tem, which consists of four major components and one schema to coordinate the components. The system can take a random podcast episode audio as input and generate an around 1 minute long trailer for it. This thesis also proposes two human-based podcast trailer evaluation approaches, and the evaluation results show that the proposed system outperforms the baseline with a large margin and achieves promising results in terms of both aesthetics and functionality.
27
Stanford, Derek C. « Fast automatic unsupervised image segmentation and curve detection in spatial point patterns / ». Thesis, Connect to this title online ; UW restricted, 1999. http://hdl.handle.net/1773/8976.
Texte intégral
28
Zelmann, Rina. « Automatic detection and analysis of high frequency oscillations in the human electroencephalogram ». Thesis, McGill University, 2013. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=114313.
Texte intégralRésumé :
High Frequency Oscillations (HFOs; 80-500Hz) are spontaneous short-duration small-amplitude EEG patterns that are emerging as a biomarker of tissue capable of generating epileptic seizures. In order to propel the clinical utilization and systematic study of HFOs, it is important to develop robust automatic detectors and to provide a framework to ensure stability in their identification; this is the first goal of this thesis. Although HFOs have mostly been studied with intracranial electrodes, they have also been recorded on the scalp. A fundamental question is to understand how is it possible to see these small events on the scalp given the powerful skull attenuation; this is the second goal of this thesis. The first goal is addressed by designing a procedure to systematize the study of HFOs and by developing an automatic detector. A procedure that allows to control for consistency among readers and to evaluate if a selected interval provides stable information, for automatic and visual identification of HFOs, is first presented. This procedure is now routinely used when identifying interictal HFOs. This study is the first to evaluate the minimum duration needed to obtain consistent information when marking the EEG and showed that analyzing 5min of interictal EEG provided the same information as longer intervals. The approach is applicable to any type of EEG event.An automatic detector of HFOs is then described, which takes an original approach in first detecting baseline segments free of oscillatory activity and then using a statistical threshold obtained from these local baselines to detect HFOs. The detector performs better than other detectors, in particular in active channels and in channels without clear baseline. A comparison of existing detectors on the same dataset is presented to analyze their performance, to show that optimizing on a particular type of data improves performance in any detector, and to emphasize the issues involved in validation. The second goal of this thesis is the study of the spatial distribution of cortical activity at the time of scalp HFOs. As HFOs are produced by small brain regions, and since the EEG is greatly attenuated before reaching the scalp, HFOs are mostly recorded with intracranial electrodes. Surprisingly, HFOs have been recently observed also on the scalp EEG. Using simultaneous scalp and intracranial recordings, we showed that even though the generators of HFOs have small spatial extent, they can be observed on the scalp with small amplitude and focal extent. We showed that these small extent events are undersampled on the scalp with the density of standard electrode systems, and on cortical grids with the standard inter-electrode spacing of 1cm. A dense distribution of scalp electrodes seems necessary to fully spatially sample HFOs on the scalp. This opens the possibility of systematically studying HFOs non-invasively. By developing methods for the detection and analysis of HFOs, we expect to improve the systematic study of intracranial and scalp HFOs, moving towards their clinical application as a biomarker of epileptogenic tissue.Les oscillations de haute fréquence (OHF; 80-500 Hz) constituent des évènements EEG spontanés de courte durée et de faible amplitude qui émergent en tant que biomarqueur du tissu pouvant générer les crises épileptiques. Afin de promouvoir l'utilisation clinique et l'étude systématique des OHF, il est important de développer des détecteurs automatiques fiables et de fournir un cadre visant à garantir la stabilité de leurs résultats. Il s'agit là du premier objectif de la présente thèse. Les OHF ont principalement été étudiées à partir d'électrodes intracrâniennes, mais elles ont également été enregistrées à l'aide d'électrodes placées sur le cuir chevelu. Il convient alors de comprendre comment l'on peut observer ces évènements de faible envergure du fait de l'atténuation importante du crâne, ce qui constitue le second objectif de cette thèse. Pour répondre au premier objectif, nous avons conçu une procédure visant à systématiser l'étude des OHF et avons élaboré un détecteur automatique. Ainsi, nous présentons d'abord une procédure permettant d'assurer l'uniformité entre les lecteurs et d'évaluer si un intervalle choisi offre des renseignements stables pour un repérage visuel et automatique des OHF. À l'heure actuelle, cette procédure est communément utilisée quand les OHF interictales sont repérées. Cette étude est la première à évaluer la durée minimale nécessaire à l'obtention de renseignements cohérents pour le marquage des EEG et elle a démontré que l'analyse de 5 minutes d'EEG interictal offre la même information que des intervalles de plus longue durée. Cette approche est applicable à tout type d'évènements EEG. Nous avons ensuite décrit un détecteur automatique d'OHF, qui suit une approche originale en détectant d'abord des segments de base dénués d'activités oscillatoires avant d'utiliser un seuil statistique obtenu à partir de ces valeurs de base locales pour déterminer les OHF. Ce détecteur est plus efficace que d'autres détecteurs, notamment pour les canaux actifs et les canaux sans valeur de base claire. Une comparaison entre les détecteurs existants pour le même ensemble de données est présentée afin d'analyser leur performance respective, de démontrer que l'optimisation d'un certain type de données améliore l'efficacité de tous les détecteurs et de mettre en évidence les problèmes en jeu dans la validation. Le second objectif de la présente thèse est d'étudier la distribution spatiale de l'activité corticale au moment des OHF enregistrées sur le cuir chevelu. Dans la mesure où les OHF sont produites par de petites régions cérébrales et que l'EEG est fortement atténué avant d'arriver au cuir chevelu, les OHF sont surtout enregistrées à l'aide d'électrodes intracrâniennes. Il est étonnant que dernièrement, des OHF aient également été observées sur des EEG enregistrés sur le cuir chevelu. En se basant sur les enregistrements simultanés sur le cuir chevelu et intracrâniens, nous avons démontré que, même si les régions génératrices d'OHF sont faiblement étendues sur le plan spatial, les OHF peuvent être observées à l'aide d'électrodes placées sur le cuir chevelu avec une faible amplitude et une étendue focale. Nous avons établi que ces évènements de faible étendue sont sous-échantillonnés sur le cuir chevelu avec la densité des systèmes standards d'électrodes et sur les grilles corticales avec l'espacement standard de 1 cm entre les électrodes. Il semble nécessaire d'avoir une répartition dense des électrodes sur le cuir chevelu afin de représenter spatialement de façon exhaustive les OHF enregistrées sur le cuir chevelu. Cela ouvrirait la voie à une étude systématique non invasive des OHF. Avec l'élaboration de méthodes de détection et d'analyse des OHF, nous souhaitons améliorer l'étude systématique des OHF intracrâniennes et du cuir chevelu, dans l'optique d'une application clinique en tant que biomarqueur du tissu épileptogène.
29
Nickels, Michael R. « IMPROVING MOTION IMAGERY ANALYSIS : INVESTIGATING DETECTION FAILURES, REMEMBERING TO PERFORM DEFERRED INTENTIONS ». Wright State University / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=wright1409316622.
Texte intégral
30
Cesbron, Fred́eŕique Chantal. « Pitch detection using the short-term phase spectrum ». Thesis, Georgia Institute of Technology, 1992. http://hdl.handle.net/1853/15503.
Texte intégral
31
Pokric, Boris. « Laser based machine vision for three-dimensional surface analysis ». Thesis, Leeds Beckett University, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.297358.
Texte intégral
32
Aldwihe, Ramez. « Computer vision for driving support systems : automatic traffic signs detection and proximity analysis ». Master's thesis, Universidade de Évora, 2018. http://hdl.handle.net/10174/23063.
Texte intégralRésumé :
The future of the automotive industry in the coming years will depend heavily on artificial intelligence techniques. This thesis proposes a technique for automatic detection and recognition of traffic signs from images, to provide a driver alert system. The system developed in this work includes algorithms to detect, classify and recognize traffic signs, based on a set belonging to a German database. The main signs are circular and triangular, which have two different colors, namely red and blue. Several examples of images, in different scenarios, are taken from the German roads, and are used to test the effectiveness of the proposed system. Traffic signs are detected by analyzing the color and shape information. The detected signs are classified accordingtotheCNNMachineLearningtechnique,andcanbeclassifiedinto43differentclassesaccording to previous classification already existing in the reference database. After detecting the presence of a traffic signs, the traffic signs is detected by comparing the traffic signs detected in the images with the signs in the database. The overall recognition accuracy is 75 % and processing is normally done in 1.6 seconds. This project is implemented with the OpenCV tool and the Python programming language; Sumário:
Visão Computacional aplicada a sistemas de apoio à condução: deteção automática de sinalização de trânsito e análise de proximidade
O futuro da indústria automóvel nos próximos anos irá depender fortemente das técnicas de inteligência artificial. Esta tese propõe uma técnica para a deteção automática e o reconhecimento de sinais de trânsito a partir de imagens, para proporcionar um sistema de alerta ao condutor. O sistema desenvolvido neste trabalho inclui algoritmos para detetar, classificar e reconhecer sinais de trânsito, nomeadamente um conjunto pertencente a uma base de dados alemã. Osprincipaissinaissãocircularesetriangulares,osquaistêmduascoresdiferentes,nomeadamentevermelho e azul. Vários exemplos de imagens, em diferentes cenários, são tirados das estradas alemãs, e são usados para testar a eficácia do sistema proposto. Os sinais de trânsito são detetados analisando a informação de cor e forma. Os sinais detetados são classificadosapartirdatécnicaCNNMachineLearning, podendoserclassificadosem43classesdiferentes, de acordo com classificação prévia já existente na base de dados de referência. Após deteção da presença de um sinal de trânsito, o reconhecimento do mesmo é feito comparando os sinais de trânsito detetados nas imagens com os sinais existentes na base de dados. Oacertodoreconhecimentogeraléde75%eoprocessamentoéfeitonormalmenteem1.6segundos. Este projeto for implementado com a ferramenta OpenCV e a linguagem de programação Python.
33
Abedan, Kondori Farid. « Bring Your Body into Action : Body Gesture Detection, Tracking, and Analysis for Natural Interaction ». Doctoral thesis, Umeå universitet, Institutionen för tillämpad fysik och elektronik, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-88508.
Texte intégralRésumé :
Due to the large influx of computers in our daily lives, human-computer interaction has become crucially important. For a long time, focusing on what users need has been critical for designing interaction methods. However, new perspective tends to extend this attitude to encompass how human desires, interests, and ambitions can be met and supported. This implies that the way we interact with computers should be revisited. Centralizing human values rather than user needs is of the utmost importance for providing new interaction techniques. These values drive our decisions and actions, and are essential to what makes us human. This motivated us to introduce new interaction methods that will support human values, particularly human well-being. The aim of this thesis is to design new interaction methods that will empower human to have a healthy, intuitive, and pleasurable interaction with tomorrow’s digital world. In order to achieve this aim, this research is concerned with developing theories and techniques for exploring interaction methods beyond keyboard and mouse, utilizing human body. Therefore, this thesis addresses a very fundamental problem, human motion analysis. Technical contributions of this thesis introduce computer vision-based, marker-less systems to estimate and analyze body motion. The main focus of this research work is on head and hand motion analysis due to the fact that they are the most frequently used body parts for interacting with computers. This thesis gives an insight into the technical challenges and provides new perspectives and robust techniques for solving the problem.
34
Herman, Stephanie. « Automatic detection of protein degradation markers in mass spectrometry imaging ». Thesis, Uppsala universitet, Institutionen för biologisk grundutbildning, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-275072.
Texte intégralRésumé :
Today we are collecting a large amount of tissue samples to store for future studies of different health conditions, in hopes that the focus in health care will shift from treatments to early detection and prevention, by the use of biomarkers. To make sure that the storing of tissue is done in a reliable way, where the molecular profile of the samples are preserved, we first need to characterise how these changes occur. In this thesis, data from mice brains were collected using MALDI imaging mass spectrometry (IMS) and an analysis pipeline for robust MALDI IMS data handling and evaluation was implemented. The finished pipeline contains two reduction algorithms, catching images with interesting intensity features, while taking the spatial information into account, along with a robust similarity measurement, for measuring the degree of co-localisation. It also includes a clustering algorithm built upon the similarity measurement and an amino acid mass comparer, iteratively generating combinations of amino acids for further mass comparisons with mass differences between cluster members. Availability: The source code is available at https://github.com/stephanieherman/thesis
35
Foghammar, Nömtak Carl. « Automatic SLAMS detection and magnetospheric classification in MMS data ». Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-285533.
Texte intégralRésumé :
Short Large-Amplitude Magnetic Structures (SLAMS) have been observedby spacecraft near Earth’s quasi-parallel bow shock. They arecharacterized by a short and sudden increase of the magnetic field,usually by a factor of 2 or more. SLAMS studies have previously beenlimited to small sample sizes because SLAMS were identified throughmanual inspection of the spacecraft data. This makes it difficult to drawgeneral conclusions and the subjective element complicates collaborationbetween researchers. A solution is presented in this thesis; anautomatic SLAMS detection algorithm. We investigate several movingwindowmethods and measure their performance on a set of manuallyidentified SLAMS. The best algorithm is then used to identify 98406SLAMS in data from the Magnetospheric Multiscale (MMS) mission. Ofthose, 66210 SLAMS were detected when the Fast Plasma Investigation(FPI) instrument was active. Additionally, we are interested in knowingwhether a detected SLAMS is located in the foreshock or magnetosheath.Therefore, we implement a Gaussian mixture model classifier,based on hierarchical clustering of the FPI data, that can separatebetween the four distinct regions of the magnetosphere that MMSencounters; magnetosphere, magnetosheath, solar wind and (ion) foreshock.The identified SLAMS are compiled into a database which holdstheir start and stop dates, positional coordinates, B-field informationand information from the magnetospheric classifier to allow for easyfiltering to a specific SLAMS population. To showcase the potentialof the database we use it to perform preliminary statistical analysison how the properties of SLAMS are affected by its spatial and/ormagnetospheric location. The database and Matlab implementationare available on github: https://github.com/cfognom/MMS_SLAMS_detection_and_magnetospheric_classification.Korta magnetiska strukturer med hög amplitud (SLAMS) har observeratsav satelliter nära jordens kvasi-parallella bogchock. En kortoch plötslig höjning av magnetfältsstyrkan är ett typiskt drag förSLAMS, vanligtvis med en faktor 2 eller mer. Forskning om SLAMShar tidigare varit begränsad till mindre fallstudier eftersom SLAMSidentifierats genom manuell inspektion av satellitdata. Detta gör detsvårt att dra generella slutsatser och det subjektiva elementet försvårarsamarbetet mellan forskare. En lösning till detta problem presenteras idenna avhandling; en automatisk identifieringsalgoritm för SLAMS. Viundersöker flera metoder och mäter deras prestanda på en uppsättningmanuellt identifierade SLAMS. Den bästa algoritmen används sedan föratt identifiera 98406 SLAMS i data från MMS-uppdraget. Av dessa upptäcktes66210 SLAMS när FPI-instrumentet var aktivt. Vi är dessutomintresserade av att veta om en upptäckt SLAMS finns i förshocken ellermagnetoskiktet. Därför implementerar vi en Gaussisk klassificeraresom bygger på hierarkisk klustring av FPI-data. Den kan separerade fyra distinkta regionerna av magnetosfären som MMS observerar;magnetosfär, magnetoskikt, solvind och (jon) förchock. De identifieradeSLAMS:en sammanställs till en databas som innehåller deras start- ochstoppdatum, positionskoordinater, B-fältsinformation och informationfrån magnetosfärsklassificeraren för att möjliggöra enkel filtrering tillen specifik SLAMS-population. För att visa potentialen av databasenutför vi en preliminär statistisk undersökning av hur egenskapernaav SLAMS påverkas av deras rumsliga och/eller magnetosfäriska position.Databasen och Matlab-implementationen är tillgängliga på Github:https://github.com/cfognom/MMS_SLAMS_detection_and_magnetospheric_classification.
36
Moussa, Georges Fouad Mr. « EARLY FOREST FIRE DETECTION USING TEXTURE, BLOB THRESHOLD, AND MOTION ANALYSIS OF PRINCIPAL COMPONENTS ». DigitalCommons@CalPoly, 2012. https://digitalcommons.calpoly.edu/theses/881.
Texte intégralRésumé :
Forest fires constantly threaten ecological systems, infrastructure and human lives. The purpose behind this study is minimizing the devastating damage caused by forest fires. Since it is impossible to completely avoid their occurrences, it is essential to accomplish a fast and appropriate intervention to minimize their destructive consequences. The most traditional method for detecting forest fires is human based surveillance through lookout towers. However, this study presents a more modern technique. It utilizes land-based real-time multispectral video processing to identify and determine the possibility of fire occurring within the camera’s field of view. The temporal, spectral, and spatial signatures of the fire are exploited. The methods discussed include: (1) Range filtering followed by entropy filtering of the infrared (IR) video data, and (2) Principal Component Analysis of visible spectrum video data followed by motion analysis and adaptive intensity threshold. The two schemes presented are tailored to detect the fire core, and the smoke plume, respectively.
Cooled Midwave Infrared (IR) camera is used to capture the heat distribution within the field of view. The fire core is then isolated using texture analysis techniques: first, range filtering applied on two consecutive IR frames, and then followed by entropy filtering of their absolute difference.
Since smoke represents the earliest sign of fire, this study also explores multiple techniques for detecting smoke plumes in a given scene. The spatial and temporal variance of smoke plume is captured using temporal Principal Component Analysis, PCA. The results show that a smoke plume is readily segmented via PCA applied on the visible Blue band over 2 seconds sampled every 0.2 seconds. The smoke plume exists in the 2nd principal component, and is finally identified, segmented, and isolated, using either motion analysis or adaptive intensity threshold.
Experimental results, obtained in this study, show that the proposed system can detect smoke effectively at a distance of approximately 832 meters with a low false-alarm rate and short reaction time. Applied, such system would achieve early forest fire detection minimizing fire damage.
Keywords: Image Processing, Principal Component Analysis, PCA, Principal Component, PC, Texture Analysis, Motion Analysis, Multispectral, Visible, Cooled Midwave Infrared, Smoke Signature, Gaussian Mixture Model.
37
Labuschagne, P. J. « Automatic clustering with application to time dependent fault detection in chemical processes ». Pretoria : [s.n.], 2009. http://upetd.up.ac.za/thesis/available/etd-07062009-142237.
Texte intégral
38
Lennartsson, Richard. « Automatic diagnostic system for I-shift transmission using vibration analysis ». Thesis, Linköping University, Automatic Control, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-57732.
Texte intégralRésumé :
This master’s thesis work was performed at Volvo Powertrain in Köping, Sweden, which manufactures gearboxes and integrated transmission systems for heavy vehicles. The thesis is a continuation of a previous master’s thesis performed at the Köping factory in 2009. After manufacturing and assembly, each gearbox is manually validated to ensure the gearbox quality and functionality. When validating the gearbox gears, the operator shifts the gearbox in a predefined manner and listens for irregularities. If an error sound is heard the operator must then locate the source of error. With numerous of cog wheels rotating at the same time this task requires extensive knowledge and experience of the operator. The main objective is to develop an automatic diagnostic system for detection of cog errors and assist the operator in the process of locating the faulty component.
The work consists of two parts. In the first part the automatic diagnostic system is developed and a database of gearbox recordings is stored. The amounts of logged non-faulty gearboxes are significantly much larger (50) than the logged faulty gearboxes (1). Therefore, when determining thresholds needed for the diagnosis, the data obtained from the non-faulty gearboxes are used. Two statistical methods are presented to extract the thresholds. The first method uses an extremevalue distribution and the other method a Gaussian distribution. When validated, both methods did successfully detect on cog faults. In the second part an investigation is made of how shaft imbalance can be detected and implemented in the developed system.
Volvo Powertrain continually follows-up all faults found at the validation station to ensure the quality of their work and eliminate the sources of error. During system testing one logged gearbox was found faulty. The automatic diagnostic system did successfully detect and locate the faulty component which later also was confirmed when the gearbox was dismounted. With only one detected error it is difficult to conclude the system performance and further testing is required. However, during the testing no false detections were made.
39
Azarbarzin, Ali. « Snoring sounds analysis : automatic detection, higher order statistics, and its application for sleep apnea diagnosis ». IEEE, 2011. http://hdl.handle.net/1993/9593.
Texte intégralRésumé :
Snoring is a highly prevalent disorder affecting 20-40% of adult population. Snoring
is also a major indicative of obstructive sleep apnea (OSA). Despite the magnitude of effort, the acoustical properties of snoring in relation to physiological states are not yet known.
This thesis explores statistical properties of snoring sounds and their association with OSA. First, an unsupervised technique was developed to automatically extract the snoring sound segments from the lengthy recordings of respiratory sounds.
This technique was tested over 5665 snoring sound segments of 30 participants and the detection accuracy of 98.6% was obtained. Second, the relationship between anthropometric parameters of snorers with different degrees of obstruction and their snoring sounds’ statistical characteristics
was investigated. Snoring sounds are non-Gaussian in nature; thus second order statistical methods such as power spectral analysis would be inadequate to extract information from snoring sounds. Therefore, higher order statistical features, in addition to the second order ones, were extracted. Third, the variability of snoring sound segments within and between 57 snorers with and without OSA was investigated. It was found that the sound characteristics
of non-apneic (when there is no apneic event), hypopneic (when there is hypopnea), and post-apneic (after apnea) snoring events were significantly different.
Then, this variability of snoring sounds was used as a signature to discriminate the non-OSA snorers from OSA snorers. The accuracy was found to be 96.4%.
Finally, it was observed that some snorers formed distinct clusters of snoring sounds in a multidimensional feature space. Hence, using Polysomnography (PSG) information, the dependency of snoring sounds on body position, sleep stage, and blood oxygen level was investigated. It was found that all the three variables affected snoring sounds. However, body position was found to have the highest effect on the characteristics of snoring sounds.
In conclusion, snoring sounds analysis offers valuable information on the upper airway physiological state and pathology. Thus, snoring sound analysis may further
find its use in determining the exact state and location of obstruction.
40
Chen, Huaqing. « Analysis and processing of HRCT images of the lung for automatic segmentation and nodule detection ». Thesis, University of Canterbury. Computer Science and Software Engineering, 2012. http://hdl.handle.net/10092/6742.
Texte intégralRésumé :
Automatic lung segmentation and lung nodule detection through High-
Resolution Computed Tomography (HRCT) image is a new and exciting research
in the area of medical image processing and analysis. In this research, two new
techniques for segmentation of lung regions and extraction of nodules on the
HRCT image are proposed. An automatic lung segmentation system is proposed for
identifying the lungs in HRCT lung images. First, lung regions are extracted from
the HRCT images by grey-level thresholding. The lung background information is
eliminated by linear scans originating from border pixels. Finally, lung boundaries
are smoothed along the mediastinum. The lung nodule extraction from the HRCT
image is processed based on a set of continuous HRCT slices of lung images. In the
first stage, the abnormal areas are extracted based on nodule pixel collection and
combination. In the final stage, the abnormal area is extracted by comparing the
density and shape profile. Both of the systems have been tested by processing data
sets from 10 continuous image sets (100 images). Lung segmentation results are
presented by comparing our automatic method to manually traced borders.
Averaged over all results, the accuracy of lung segmentation is 96.10%. The
proposed nodule detection method has been tested on image sets containing healthy
and unhealthy lung images. Statistical analysis has been done and the results show
the overall nodule detection rate is 88.44% along with the false positive rate of 0.18.
41
KHAN, SULTAN DAUD. « Automatic Detection and Computer Vision Analysis of Flow Dynamics and Social Groups in Pedestrian Crowds ». Doctoral thesis, Università degli Studi di Milano-Bicocca, 2016. http://hdl.handle.net/10281/102644.
Texte intégralRésumé :
Computer vision played a vital role in the field of video surveillance. However, recent developed computer vision algorithms rarely solve the problems related to real time crowd management. The phenomena of crowd like sports, festivals, concerts, political gatherings etc, are mostly observed in urban areas, which attracts hundreds of thousands people. In this thesis, we have developed algorithms that overcome some of the challenges encountered in videos of crowded environments such as sporting events, religious festivals, parades, concerts, train stations, airports, and malls. The main theme of this thesis is two fold ,i.e, understanding crowd dynamics in videos of (i), high density crowds and (ii) low density crowds. Typical examples of high density crowds include marathons, religious festivals while malls, airports, subways etc covers low dense situations. In this thesis, we adopt different approaches in order to deal with different kinds of problems coming from these two categories of crowd.
In particular, first part of the thesis, we adopt holistic approach to generate a global representation of the scene that captures both dynamics of the crowd and structure of the scene. This was achieved by extracting global features, i.e optical flow from the scene. For the crowd flow segmentation problem, the optical flows vectors are clustered by using K-means clustering followed by the blob absorption approach. Using the segmentation information, we continue to estimate the number of people in each segment by carrying out the blob analysis and blob size optimization approach. This approach however, provide useful information for understanding crowd dynamics yet it lacks significant information for understanding crowd behavior. Therefore, in this thesis, the current crowd flow segmentation and counting approach is further extended in order to coup the challenges of crowd behavior understanding. The extension adopts optical flow for the identification of pedestrian movements, and it considers the analyzed video as a set of sequences. The latter are analyzed separately, producing tracklets that are then clustered to produce global trajectories, defining both sources and sinks, but also characterizing the movement of pedestrians in the scene.
In the second part of the thesis, We propose a novel approach for automatic detection of social groups of pedestrians in crowds by considering only start (source) and stop (sink) locations of pedestrian trajectories. We build an Association Matrix that captures the joint probability distribution of starts and stops locations of all pedestrian trajectories to all other pedestrian trajectories in the scene. Pedestrians exhibiting similar distribution are combining in a group, where as similarity among the distributions is measuread by KL Divergence We adopt bottom-up hierarchical clustering approach, which is three step processes. In first step, we treat all the individuals as independent clusters, In the second step, couples are detected and after pruning of bad couples, Adjacency matrix is generated. Later on, in step three, using the Adjacency Matrix, groups of couples, those have strong intergroup closeness (similarity) are merged into a larger group..
42
D'AMATO, VINCENZO STEFANO. « Deep Multi Temporal Scale Networks for Human Motion Analysis ». Doctoral thesis, Università degli studi di Genova, 2023. https://hdl.handle.net/11567/1104759.
Texte intégralRésumé :
The movement of human beings appears to respond to a complex motor system that contains signals at different hierarchical levels.
For example, an action such as ``grasping a glass on a table'' represents a high-level action, but to perform this task, the body needs several motor inputs that include the activation of different joints of the body (shoulder, arm, hand, fingers, etc.).
Each of these different joints/muscles have a different size, responsiveness, and precision with a complex non-linearly stratified temporal dimension where every muscle has its temporal scale.
Parts such as the fingers responds much faster to brain input than more voluminous body parts such as the shoulder.
The cooperation we have when we perform an action produces smooth, effective, and expressive movement in a complex multiple temporal scale cognitive task.
Following this layered structure, the human body can be described as a kinematic tree, consisting of joints connected.
Although it is nowadays well known that human movement and its perception are characterised by multiple temporal scales, very few works in the literature are focused on studying this particular property.
In this thesis, we will focus on the analysis of human movement using data-driven techniques.
In particular, we will focus on the non-verbal aspects of human movement, with an emphasis on full-body movements.
The data-driven methods can interpret the information in the data by searching for rules, associations or patterns that can represent the relationships between input (e.g. the human action acquired with sensors) and output (e.g. the type of action performed).
Furthermore, these models may represent a new research frontier as they can analyse large masses of data and focus on aspects that even an expert user might miss.
The literature on data-driven models proposes two families of methods that can process time series and human movement.
The first family, called shallow models, extract features from the time series that can help the learning algorithm find associations in the data.
These features are identified and designed by domain experts who can identify the best ones for the problem faced.
On the other hand, the second family avoids this phase of extraction by the human expert since the models themselves can identify the best set of features to optimise the learning of the model.
In this thesis, we will provide a method that can apply the multi-temporal scales property of the human motion domain to deep learning models, the only data-driven models that can be extended to handle this property.
We will ask ourselves two questions: what happens if we apply knowledge about how human movements are performed to deep learning models? Can this knowledge improve current automatic recognition standards?
In order to prove the validity of our study, we collected data and tested our hypothesis in specially designed experiments.
Results support both the proposal and the need for the use of deep multi-scale models as a tool to better understand human movement and its multiple time-scale nature.
43
Park, Dong-Jun. « Video event detection framework on large-scale video data ». Diss., University of Iowa, 2011. https://ir.uiowa.edu/etd/2754.
Texte intégralRésumé :
Detection of events and actions in video entails substantial processing of very large, even open-ended, video streams. Video data presents a unique challenge for the information retrieval community because properly representing video events is challenging. We propose a novel approach to analyze temporal aspects of video data. We consider video data as a sequence of images that form a 3-dimensional spatiotemporal structure, and perform multiview orthographic projection to transform the video data into 2-dimensional representations. The projected views allow a unique way to rep- resent video events and capture the temporal aspect of video data. We extract local salient points from 2D projection views and perform detection-via-similarity approach on a wide range of events against real-world surveillance data. We demonstrate our example-based detection framework is competitive and robust. We also investigate the synthetic example driven retrieval as a basis for query-by-example.
44
Nawarathna, Ruwan D. « Detection of Temporal Events and Abnormal Images for Quality Analysis in Endoscopy Videos ». Thesis, University of North Texas, 2013. https://digital.library.unt.edu/ark:/67531/metadc283849/.
Texte intégralRésumé :
Recent reports suggest that measuring the objective quality is very essential towards the success of colonoscopy. Several quality indicators (i.e. metrics) proposed in recent studies are implemented in software systems that compute real-time quality scores for routine screening colonoscopy. Most quality metrics are derived based on various temporal events occurred during the colonoscopy procedure. The location of the phase boundary between the insertion and the withdrawal phases and the amount of circumferential inspection are two such important temporal events. These two temporal events can be determined by analyzing various camera motions of the colonoscope. This dissertation put forward a novel method to estimate X, Y and Z directional motions of the colonoscope using motion vector templates. Since abnormalities of a WCE or a colonoscopy video can be found in a small number of frames (around 5% out of total frames), it is very helpful if a computer system can decide whether a frame has any mucosal abnormalities. Also, the number of detected abnormal lesions during a procedure is used as a quality indicator. Majority of the existing abnormal detection methods focus on detecting only one type of abnormality or the overall accuracies are somewhat low if the method tries to detect multiple abnormalities. Most abnormalities in endoscopy images have unique textures which are clearly distinguishable from normal textures. In this dissertation a new method is proposed that achieves the objective of detecting multiple abnormalities with a higher accuracy using a multi-texture analysis technique. The multi-texture analysis method is designed by representing WCE and colonoscopy image textures as textons.
45
Al, saddik Hania. « Spectral and textural analysis of high resolution data for the automatic detection of grape vine diseases ». Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCK050/document.
Texte intégralRésumé :
La Flavescence dorée est une maladie contagieuse et incurable de la vigne détectable sur les feuilles. Le projet DAMAV (Détection Automatique des MAladies de la Vigne) a été mis en place, avec pour objectif de développer une solution de détection automatisée des maladies de la vigne à l’aide d’un micro-drone. Cet outil doit permettre la recherche des foyers potentiels de la Flavescence dorée, puis plus généralement de toute maladie détectable sur le feuillage à l’aide d’un outil multispectral dédié haute résolution.Dans le cadre de ce projet, cette thèse a pour objectif de participer à la conception et à l’implémentation du système d’acquisition multispectral et de développer les algorithmes de prétraitement d’images basés sur les caractéristiques spectrales et texturales les plus pertinentes reliées à la Flavescence dorée.Plusieurs variétés de vigne ont été considérées telles que des variétés rouges et blanches; de plus, d’autres maladies que ‘Flavescence dorée’ (FD) telles que Esca et ‘Bois noir’ (BN) ont également été testées dans des conditions de production réelles. Le travail de doctorat a été essentiellement réalisé au niveau feuille et a impliqué une étape d’acquisition suivie d’une étape d’analyse des données.La plupart des techniques d'imagerie, même multispectrales, utilisées pour détecter les maladies dans les grandes cultures ou les vignobles, opèrent dans le domaine du visible. Dans DAMAV, il est conseillé que la maladie soit détectée le plus tôt possible. Des informations spectrales sont nécessaires, notamment dans l’infrarouge. Les réflectances des feuilles des plantes peuvent être obtenues sur les longueurs d'onde les plus courtes aux plus longues. Ces réflectances sont intimement liées aux composants internes des feuilles. Cela signifie que la présence d'une maladie peut modifier la structure interne des feuilles et donc altérer sa signature.Un spectromètre a été utilisé sur le terrain pour caractériser les signatures spectrales des feuilles à différents stades de croissance. Afin de déterminer les réflectances optimales pour la détection des maladies (FD, Esca, BN), une nouvelle méthodologie de conception d'indices de maladies basée sur deux techniques de réduction de dimensions, associées à un classifieur, a été mise en place. La première technique de sélection de variables utilise les Algorithmes Génétiques (GA) et la seconde s'appuie sur l'Algorithme de Projections Successives (SPA). Les nouveaux indices de maladies résultants surpassent les indices de végétation traditionnels et GA était en général meilleur que SPA. Les variables finalement choisies peuvent ainsi être mises en oeuvre en tant que filtres dans le capteur MS.Les informations de réflectance étaient satisfaisantes pour la recherche d’infections (plus que 90% de précision pour la meilleure méthode) mais n’étaient pas suffisantes. Ainsi, les images acquises par l’appareil MS peuvent être ensuite traitées par des techniques bas-niveau basées sur le calcul de paramètres de texture puis injectés dans un classifieur. Plusieurs techniques de traitement de texture ont été testées mais uniquement sur des images couleur. Une nouvelle méthode combinant plusieurs paramètres texturaux a été élaborée pour en choisir les meilleurs. Nous avons constaté que les informations texturales pouvaient constituer un moyen complémentaire non seulement pour différencier les feuilles de vigne saines des feuilles infectées (plus que 85% de précision), mais également pour classer le degré d’infestation des maladies (plus que 74% de précision) et pour distinguer entre les maladies (plus que 75% de précision). Ceci conforte l’hypothèse qu’une caméra multispectrale permet la détection et l’identification de maladies de la vigne en plein champ‘Flavescence dorée’ is a contagious and incurable disease present on the vine leaves. The DAMAV project (Automatic detection of Vine Diseases) aims to develop a solution for automated detection of vine diseases using a micro-drone. The goal is to offer a turnkey solution for wine growers. This tool will allow the search for potential foci, and then more generally any type of detectable vine disease on the foliage. To enable this diagnosis, the foliage is proposed to be studied using a dedicated high-resolution multispectral camera.The objective of this PhD-thesis in the context of DAMAV is to participate in the design and implementation of a Multi-Spectral (MS) image acquisition system and to develop the image pre-processing algorithms, based on the most relevant spectral and textural characteristics related to ‘Flavescence dorée’.Several grapevine varieties were considered such as red-berried and white-berried ones; furthermore, other diseases than ‘Flavescence dorée’ (FD) such as Esca and ‘Bois noir’ (BN) were also tested under real production conditions. The PhD work was basically performed at a leaf-level scale and involved an acquisition step followed by a data analysis step.Most imaging techniques, even MS, used to detect diseases in field crops or vineyards, operate in the visible electromagnetic radiation range. In DAMAV, it is advised to detect the disease as early as possible. It is therefore necessary to investigate broader information in particular in the infra-red. Reflectance responses of plants leaves can be obtained from short to long wavelengths. These reflectance signatures describe the internal constituents of leaves. This means that the presence of a disease can modify the internal structure of the leaves and hence cause an alteration of its reflectance signature.A spectrometer is used in our study to characterize reflectance responses of leaves in the field. Several samples at different growth stages were used for the tests. To define optimal reflectance features for grapevine disease detection (FD, Esca, BN), a new methodology that designs spectral disease indices based on two dimension reduction techniques, coupled with a classifier, has been developed. The first feature selection technique uses the Genetic Algorithms (GA) and the second one relies on the Successive Projection Algorithm (SPA). The new resulting spectral disease indices outperformed traditional vegetation indices and GA performed in general better than SPA. The features finally chosen can thus be implemented as filters in the MS sensor.In general, the reflectance information was satisfying for finding infections (higher than 90% of accuracy for the best method) but wasn’t enough. Thus, the images acquired with the developed MS device can further be pre-processed by low level techniques based on the calculation of texture parameters injected into a classifier. Several texture processing techniques have been tested but only on colored images. A method that combines many texture features is elaborated, allowing to choose the best ones. We found that the combination of optimal textural information could provide a complementary mean for not only differentiating healthy from infected grapevine leaves (higher than 85% of accuracy), but also for grading the disease severity stages (higher than 73% of accuracy) and for discriminating among diseases (higher than 72% of accuracy). This is in accordance with the hypothesis that a multispectral camera can enable detection and identification of diseases in grapevine fields
46
Feng, Qianli. « Automatic American Sign Language Imitation Evaluator ». The Ohio State University, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=osu1461233570.
Texte intégral
47
Shreve, Matthew Adam. « Automatic Macro- and Micro-Facial Expression Spotting and Applications ». Scholar Commons, 2013. http://scholarcommons.usf.edu/etd/4770.
Texte intégralRésumé :
Automatically determining the temporal characteristics of facial expressions has extensive application domains such as human-machine interfaces for emotion recognition, face identification, as well as medical analysis. However, many papers in the literature have not addressed the step of determining when such expressions occur. This dissertation is focused on the problem of automatically segmenting macro- and micro-expressions frames (or retrieving the expression intervals) in video sequences, without the need for training a model on a specific subset of such expressions. The proposed method exploits the non-rigid facial motion that occurs during facial expressions by modeling the strain observed during the elastic deformation of facial skin tissue. The method is capable of spotting both macro expressions which are typically associated with emotions such as happiness, sadness, anger, disgust, and surprise, and rapid micro- expressions which are typically, but not always, associated with semi-suppressed macro-expressions. Additionally, we have used this method to automatically retrieve strain maps generated from peak expressions for human identification. This dissertation also contributes a novel 3-D surface strain estimation algorithm using commodity 3-D sensors aligned with an HD camera. We demonstrate the feasibility of the method, as well as the improvements gained when using 3-D, by providing empirical and quantitative comparisons between 2-D and 3-D strain estimations.
48
Korzhova, Valentina N. « Motion Analysis of Fluid Flow in a Spinning Disk Reactor ». Scholar Commons, 2009. http://scholarcommons.usf.edu/etd/3478.
Texte intégralRésumé :
The ow of a liquid _lm over a rapidly rotating horizontal disk has numerous industrial applications including pharmaceuticals, chemical engineering, bioengineering, etc. The analysis and control of complex uid ows over a rapidly rotating horizontal disk is an important issue in the experimental uid mechanics. The spinning disk reactor exploits the bene_ts of centrifugal force, which produces thin highly sheared _lms due to radial acceleration. The hydrodynamics of the _lm results in excellent uid mixing and high heat or mass transfer rates.
This work focuses on developing a novel approach for uid ow tracking and analysis. Speci_cally, the developed algorithm is able to detect the moving waves and compute controlling _lm ow parameters for the uid owing over a rotating disk. The input to this algorithm is an easily acquired non-invasive video data. It is shown that under single light illumination it is possible to track specular portion of the reected light on the moving wave. Hence, the uid wave motion can be tracked and uid ow parameters can be computed. The uid ow parameters include wave velocities, wave inclination angles, and distances between consecutive waves. Once the parameters are computed, their accuracy is analyzed and compared with the solutions of the mathematical uid dynamics models based on the Navier-Stokes equations for the case of a thin _lm. The uid model predicts wave characteristics based on directly measured controlling parameters, such as disk rotation speed and uid ow rate. It is shown that the calculated parameter values approximately coincide with the predicted ones. The average computed parameters were within 5 � 10% of the predicted values.
In addition, given recovered uid characteristics and uid ow controlling parameters, full 3D wave description is obtained. That includes 3D wave location, speed, and distance between waves, as well as approximate wave thickness.
Next, the developed approach is generalized to model-based recovery of uid ow controlling parameters: the speed of the spinning disk and the initial uid-ow rate. The search in space for model parameters is performed as to minimize the error between the ow characteristics predicted by the uid dynamics model (e.g. distance between waves, wave inclination angles) and parameters recovered from video data. Results demonstrate that the speed of a disk and the ow rate are recovered with high accuracy. When compared to the ground truth available from direct observation, we noted that the controlling parameters were estimated with less than 10% error.
49
Pérez, Rúa Juan Manuel. « Hierarchical motion-based video analysis with applications to video post-production ». Thesis, Rennes 1, 2017. http://www.theses.fr/2017REN1S125/document.
Texte intégralRésumé :
Nous présentons dans ce manuscrit les méthodes développées et les résultats obtenus dans notre travail de thèse sur l'analyse du contenu dynamique de scène visuelle. Nous avons considéré la configuration la plus fréquente de vision par ordinateur, à savoir caméra monoculaire et vidéos naturelles de scène extérieure. Nous nous concentrons sur des problèmes importants généraux pour la vision par ordinateur et d'un intérêt particulier pour l'industrie cinématographique, dans le cadre de la post-production vidéo. Les problèmes abordés peuvent être regroupés en deux catégories principales, en fonction d'une interaction ou non avec les utilisateurs : l'analyse interactive du contenu vidéo et l'analyse vidéo entièrement automatique. Cette division est un peu schématique, mais elle est en fait liée aux façons dont les méthodes proposées sont utilisées en post-production vidéo. Ces deux grandes approches correspondent aux deux parties principales qui forment ce manuscrit, qui sont ensuite subdivisées en chapitres présentant les différentes méthodes que nous avons proposées. Néanmoins, un fil conducteur fort relie toutes nos contributions. Il s'agit d'une analyse hiérarchique compositionnelle du mouvement dans les scènes dynamiques. Nous motivons et expliquons nos travaux selon l'organisation du manuscrit résumée ci-dessous. Nous partons de l'hypothèse fondamentale de la présence d'une structure hiérarchique de mouvement dans la scène observée, avec un objectif de compréhension de la scène dynamique. Cette hypothèse s'inspire d'un grand nombre de recherches scientifiques sur la vision biologique et cognitive. Plus précisément, nous nous référons à la recherche sur la vision biologique qui a établi la présence d'unités sensorielles liées au mouvement dans le cortex visuel. La découverte de ces unités cérébrales spécialisées a motivé les chercheurs en vision cognitive à étudier comment la locomotion des animaux (évitement des obstacles, planification des chemins, localisation automatique) et d'autres tâches de niveau supérieur sont directement influencées par les perceptions liées aux mouvements. Fait intéressant, les réponses perceptuelles qui se déroulent dans le cortex visuel sont activées non seulement par le mouvement lui-même, mais par des occlusions, des désocclusions, une composition des mouvements et des contours mobiles. En outre, la vision cognitive a relié la capacité du cerveau à appréhender la nature compositionnelle du mouvement dans l'information visuelle à une compréhension de la scène de haut niveau, comme la segmentation et la reconnaissance d'objetsThe manuscript that is presented here contains all the findings and conclusions of the carried research in dynamic visual scene analysis. To be precise, we consider the ubiquitous monocular camera computer vision set-up, and the natural unconstrained videos that can be produced by it. In particular, we focus on important problems that are of general interest for the computer vision literature, and of special interest for the film industry, in the context of the video post-production pipeline. The tackled problems can be grouped in two main categories, according to the whether they are driven user interaction or not : user-assisted video processing tools and unsupervised tools for video analysis. This division is rather synthetic but it is in fact related to the ways the proposed methods are used inside the video post-production pipeline. These groups correspond to the main parts that form this manuscript, which are subsequently formed by chapters that explain our proposed methods. However, a single thread ties together all of our findings. This is, a hierarchical analysis of motion composition in dynamic scenes. We explain our exact contributions, together with our main motivations, and results in the following sections. We depart from a hypothesis that links the ability to consider a hierarchical structure of scene motion, with a deeper level of dynamic scene understanding. This hypothesis is inspired by plethora of scientific research in biological and psychological vision. More specifically, we refer to the biological vision research that established the presence of motion-related sensory units in the visual cortex. The discovery of these specialized brain units motivated psychological vision researchers to investigate how animal locomotion (obstacle avoidance, path planning, self-localization) and other higher-level tasks are directly influenced by motion-related percepts. Interestingly, the perceptual responses that take place in the visual cortex are activated not only by motion itself, but by occlusions, dis-occlusions, motion composition, and moving edges. Furthermore, psychological vision have linked the brain's ability to understand motion composition from visual information to high level scene understanding like object segmentation and recognition
50
Chu, Wen-Sheng. « Automatic Analysis of Facial Actions : Learning from Transductive, Supervised and Unsupervised Frameworks ». Research Showcase @ CMU, 2017. http://repository.cmu.edu/dissertations/929.
Texte intégralRésumé :
Automatic analysis of facial actions (AFA) can reveal a person’s emotion, intention, and physical state, and make possible a wide range of applications. To enable reliable, valid, and efficient AFA, this thesis investigates automatic analysis of facial actions through transductive, supervised and unsupervised learning. Supervised learning for AFA is challenging, in part, because of individual differences among persons in face shape and appearance and variation in video acquisition and context. To improve generalizability across persons, we propose a transductive framework, Selective Transfer Machine (STM), which personalizes generic classifiers through joint sample reweighting and classifier learning. By personalizing classifiers, STM offers improved generalization to unknown persons. As an extension, we develop a variant of STM for use when partially labeled data are available. Additional challenges for supervised learning include learning an optimal representation for classification, variation in base rates of action units (AUs), correlation between AUs and temporal consistency. While these challenges could be partly accommodated with an SVM or STM, a more powerful alternative is afforded by an end-to-end supervised framework (i.e., deep learning). We propose a convolutional network with long short-term memory (LSTM) and multi-label sampling strategies. We compared SVM, STM and deep learning approaches with respect to AU occurrence and intensity in and between BP4D+ [282] and GFT [93] databases, which consist of around 0.6 million annotated frames. Annotated video is not always possible or desirable. We introduce an unsupervised Branch-and-Bound framework to discover correlated facial actions in un-annotated video. We term this approach Common Event Discovery (CED). We evaluate CED in video and motion capture data. CED achieved moderate convergence with supervised approaches and enabled discovery of novel patterns occult to supervised approaches.