Dissertations / Theses on the topic 'Détection intelligente du crime'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 22 dissertations / theses for your research on the topic 'Détection intelligente du crime.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Wahl, Martine. "Contribution à la détection d'obstacles pour la voiture intelligente." Grenoble INPG, 1997. http://www.theses.fr/1997INPG0229.
Full textKhalaf, Ziad. "Contributions à l'étude de détection des bandes libres dans le contexte de la radio intelligente." Phd thesis, Supélec, 2013. http://tel.archives-ouvertes.fr/tel-00812666.
Full textKhammari, Ayoub. "Système embarqué de détection multi-sensorielle de véhicules : application à la gestion intelligente des interdistances." Paris, ENMP, 2005. http://www.theses.fr/2005ENMP1319.
Full textThis ph. D. Thesis tackles the problem of improving the robustness of vehicle detection for acc applications. In fact, one corporal accident out of four is due to a rear collision. For this sake, we combine two sensors : a frontal camera and a laser scanner. The improvement of the robustness stems from two aspects. First, we addressed the visionb based detection by developing an original approach based on fine gradient analysis, enhanced with the algorithm adaboost/ga for vehicle recognition. Then, we use the theory of evidence as a fusion framework to combine confidences delivered by the sensors and algorithms in order to improve the classification "vehicle vs. Non vehicle". The final architecture of the system is not only modular but also generic and flexible, that it could be used for other detection applications. The system was successfully implemented on lara, the prototype vehicle of the robotics center. It was evaluated at the final session of the project arcos and has demonstrated its fiability over various test scenarios elaborated specifically for acc applications
Ibrahim, Elkhatib. "Commande intelligente tolérante aux fautes des systèmes multi-sources d'énergie." Thesis, Lille 1, 2013. http://www.theses.fr/2013LIL10086/document.
Full textThis thesis presents stability analysis for a class of uncertain nonlinear systems and a method for designing robust fuzzy controllers to stabilize the multivariable multi-sources of energy systems subject to parameter uncertainties, sensor faults, actuator faults/unknown inputs and wind disturbance. First, the Takagi–Segno (TS) fuzzy model is adopted for fuzzy modeling of the uncertain nonlinear system. Next, we propose a Fuzzy Dedicated Observers (FDOS) method and a Fuzzy Proportional-Integral Estimation Observer (FPIEO) with a Fuzzy Fault Tolerant Control (FFTC) algorithm for TS systems. FDOS provide residuals for detection and isolation of sensor faults which can affect a TS model and FPIEO estimate the actuator faults which fed to the FDOS to reconfigure the controller. The concept of the Parallel Distributed Compensation (PDC) is employed to design FFTC and observers from the TS fuzzy models. Sufficient conditions are derived for robust stabilization, in the sense of Taylor series stability and Lyapunov method, for the TS fuzzy system with parametric uncertainties, sensor faults, actuator faults/unknown inputs and wind disturbance. The sufficient conditions are formulated in the format of Linear Matrix Inequalities (LMIs) and Linear Matrix Equalities (LMEs). Important issues for the stability analysis and design are remarked. The effectiveness of the proposed controller design methodology is finally demonstrated through a Hybrid Wind-Diesel System (HWDS), Wind Energy System (WES) with Doubly Fed Induction Generators (DFIG) and Photovoltaic (PV) generation system to illustrate the effectiveness of the proposed method
ROLLO, FEDERICA. "Verso soluzioni di sostenibilità e sicurezza per una città intelligente." Doctoral thesis, Università degli studi di Modena e Reggio Emilia, 2022. http://hdl.handle.net/11380/1271183.
Full textA smart city is a place where technology is exploited to help public administrations make decisions. The technology can contribute to the management of multiple aspects of everyday life, offering more reliable services to citizens and improving the quality of life. However, technology alone is not enough to make a smart city; suitable methods are needed to analyze the data collected by technology and manage them in such a way as to generate useful information. Some examples of smart services are the apps that allow to reach a destination through the least busy road route or to find the nearest parking slot, or the apps that suggest better paths for a walk based on air quality. This thesis focuses on two aspects of smart cities: sustainability and safety. The first aspect concerns studying the impact of vehicular traffic on air quality through the development of a network of traffic and air quality sensors, and the implementation of a chain of simulation models. This work is part of the TRAFAIR project, co-financed by the European Union, which is the first project with the scope of monitoring in real-time and predicting air quality on an urban scale in 6 European cities, including Modena. The project required the management of a large amount of heterogeneous data and their integration on a complex and scalable data platform shared by all the partners of the project. The data platform is a PostgreSQL database, suitable for dealing with spatio-temporal data, and contains more than 60 tables and 435 GB of data (only for Modena). All the processes of the TRAFAIR pipeline, the dashboards and the mobile apps exploit the database to get the input data and, eventually, store the output, generating big data streams. The simulation models, executed on HPC resources, use the sensor data and provide results in real-time (as soon as the sensor data are stored in the database). Therefore, the anomaly detection techniques applied to sensor data need to perform in real-time in a short time. After a careful study of the distribution of the sensor data and the correlation among the measurements, several anomaly detection techniques have been implemented and applied to sensor data. A novel approach for traffic data that employs a flow-speed correlation filter, STL decomposition and IQR analysis has been developed. In addition, an innovative framework that implements 3 algorithms for anomaly detection in air quality sensor data has been created. The results of the experiments have been compared to the ones of the LSTM autoencoder, and the performances have been evaluated after the calibration process. The safety aspect in the smart city is related to a crime analysis project, the analytical processes directed at providing timely and pertinent information to assist the police in crime reduction, prevention, and evaluation. Due to the lack of official data to produce the analysis, this project exploits the news articles published in online newspapers. The goal is to categorize the news articles based on the crime category, geolocate the crime events, detect the date of the event, and identify some features (e.g. what has been stolen during the theft). A Java application has been developed for the analysis of news articles, the extraction of semantic information through the use of NLP techniques, and the connection of entities to Linked Data. The emerging technology of Word Embeddings has been employed for the text categorization, while the Question Answering through BERT has been used for extracting the 5W+1H. The news articles referring to the same event have been identified through the application of cosine similarity to the shingles of the news articles' text. Finally, a tool has been developed to show the geolocalized events and provide some statistics and annual reports. This is the only project in Italy that starting from news articles tries to provide analyses on crimes and makes them available through a visualization tool.
Filali, Wassim. "Détection temps réel de postures humaines par fusion d'images 3D." Toulouse 3, 2014. http://thesesups.ups-tlse.fr/3088/.
Full textThis thesis is based on a computer vision research project. It is a project that allows smart cameras to understand the posture of a person. It allows to know if the person is alright or if it is in a critical situation or in danger. The cameras should not be connected to a computer but embed all the intelligence in the camera itself. This work is based on the recent technologies like the Kinect sensor of the game console. This sensor is a depth sensor, which means that the camera can estimate the distance to every point in the scene. Our contribution consists on combining multiple of these cameras to have a better posture reconstruction of the person. We have created a dataset of images to teach the program how to recognize postures. We have adjusted the right parameters and compared our program to the one of the Kinect
Ghorayeb, Hicham. "Conception et mise en œuvre d'algorithmes de vision temps-réel pour la vidéo surveillance intelligente." Phd thesis, École Nationale Supérieure des Mines de Paris, 2007. http://pastel.archives-ouvertes.fr/pastel-00003064.
Full textStanciu, Mihai Ionut. "Sur l'estimation aveugle de paramètres de signaux UWB impulsionnels dans un contexte de radio intelligente." Brest, 2011. http://www.theses.fr/2011BRES2023.
Full textThis thesis is concerned with the study of UWB systems which represent a promising perspective in low range radio systems field. UWB technology is best suited to be used within ad-hoc Piconet radio networks, which must dispose of high flexibility. Consequently this thesis is focused on one hand on the development of very low complexity parameters blind estimation methods, which can play an essential role in the synchronization stage, and on the other hand on the statistical characterization of the propagation channel, with the scope of establishing criteria to realize blind real time adjustments of the digital transmission. The study is organized in three main directions. The first consists of developing a method to estimate the chip time, based on noisy times of arrival measurements, with false and missing observations. The main problem with this approach is that the considered times of arrival statistical model cannot realistically reflect indoor UWB channels. Therefore a second direction is concerned with the development of a method to estimate the chip time based on energy measurements on the received UWB impulse radio signal. Using the well known energy detector principle this approach jointly estimates the chip time and this optimal integration window, the main advantage is that it allows considering propagation noise, multipath propagation and multiuser interference. The third direction deals with a statistical study of the multipath propagation interference of a UWB propagation channel
Ghozzi, Mohamed. "Détection cyclostationnaire des bandes de fréquences libres." Phd thesis, Université Rennes 1, 2008. http://tel.archives-ouvertes.fr/tel-00355174.
Full textDeux méthodes de détection sont envisageables. La détection d'énergie est une méthode simple, de complexité de calcul réduite et n'exigeant aucune information sur le signal à détecter, mais elle nécessite une connaissance exacte de la variance du bruit supposé blanc gaussien. La détection cyclostationnaire est plus robuste vis-à-vis des incertitudes d'estimation de la variance du bruit et capable de détecter des signaux à faibles RSB. Nous avons proposé deux algorithmes de détection cyclostationnaire. Dans le premier, la fréquence cyclique dans le signal est supposée connue, alors que dans le deuxième la cyclostationarité est détecté de manière aveugle. Cependant, pour minimiser le temps de détection des bandes libres, nous proposons une architecture hybride de détection combinant les détections d'énergie et cyclostationnaire.
Kobeissi, Hussein. "Eigenvalue Based Detector in Finite and Asymptotic Multi-antenna Cognitive Radio Systems." Thesis, CentraleSupélec, 2016. http://www.theses.fr/2016SUPL0011/document.
Full textIn Cognitive Radio, Spectrum Sensing (SS) is the task of obtaining awareness about the spectrum usage. Mainly it concerns two scenarios of detection: (i) detecting the absence of the Primary User (PU) in a licensed spectrum in order to use it and (ii) detecting the presence of the PU to avoid interference. Several SS techniques were proposed in the literature. Among these, Eigenvalue Based Detector (EBD) has been proposed as a precious totally-blind detector that exploits the spacial diversity, overcome noise uncertainty challenges and performs adequately even in low SNR conditions. The first part of this study concerns the Standard Condition Number (SCN) detector and the Scaled Largest Eigenvalue (SLE) detector. We derived exact expressions for the Probability Density Function (PDF) and the Cumulative Distribution Function (CDF) of the SCN using results from finite Random Matrix Theory; In addition, we derived exact expressions for the moments of the SCN and we proposed a new approximation based on the Generalized Extreme Value (GEV) distribution. Moreover, using results from the asymptotic RMT we further provided a simple forms for the central moments of the SCN and we end up with a simple and accurate expression for the CDF, PDF, Probability of False-Alarm, Probability of Detection, of Miss-Detection and the decision threshold that could be computed and hence provide a dynamic SCN detector that could dynamically change the threshold value depending on target performance and environmental conditions. The second part of this study concerns the massive MIMO technology and how to exploit the large number of antennas for SS and CRs. Two antenna exploitation scenarios are studied: (i) Full antenna exploitation and (ii) Partial antenna exploitation in which we have two options: (i) Fixed use or (ii) Dynamic use of the antennas. We considered the Largest Eigenvalue (LE) detector if noise power is perfectly known and the SCN and SLE detectors when noise uncertainty exists
Mousse, Ange Mikaël. "Reconnaissance d'activités humaines à partir de séquences multi-caméras : application à la détection de chute de personne." Thesis, Littoral, 2016. http://www.theses.fr/2016DUNK0453/document.
Full textArtificial vision is an involving field of research. The new strategies make it possible to have some autonomous networks of cameras. This leads to the development of many automatic surveillance applications using the cameras. The work developed in this thesis concerns the setting up of an intelligent video surveillance system for real-time people fall detection. The first part of our work consists of a robust estimation of the surface area of a person from two (02) cameras with complementary views. This estimation is based on the detection of each camera. In order to have a robust detection, we propose two approaches. The first approach consists in combining a motion detection algorithm based on the background modeling with an edge detection algorithm. A fusion approach has been proposed to make much more efficient the results of the detection. The second approach is based on the homogeneous regions of the image. A first segmentation is performed to find homogeneous regions of the image. And finally we model the background using obtained regions
Bonvard, Aurélien. "Algorithmes de détection et de reconstruction en aveugle de code correcteurs d'erreurs basés sur des informations souples." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2020. http://www.theses.fr/2020IMTA0178.
Full textRecent decades have seen the rise of digital communications. This has led to a proliferation of communication standards, requiring greater adaptability of communication systems. One way to make these systems more flexible is to design an intelligent receiver that would be able to retreive all the parameters of the transmitter from the received signal. In this manuscript, we are interested in the blind identification of error-correcting codes. We propose original methods based on the calculation of Euclidean distances between noisy symbol sequences. First, a classification algorithm allows the detection of a code and then the identification of its code words lenght. A second algorithm based on the number of collisions allows to identify the length of the information words. Then, we propose another method using the minimum Euclidean distances to identify block codes length. Finally, a method for reconstructing the dual code of an error-correcting code is presented
Birem, Merwan. "Localisation et détection de fermeture de boucle basées saillance visuelle : algorithmes et architectures matérielles." Thesis, Clermont-Ferrand 2, 2015. http://www.theses.fr/2015CLF22558/document.
Full textIn several tasks of robotics, vision is considered to be the essential element by which the perception of the environment or the interaction with other users can be realized. However, the potential artifacts in the captured images make the task of recognition and interpretation of the visual information extremely complicated. It is therefore very important to use robust, stable and high repeatability rate primitives to achieve good performance. This thesis deals with the problems of localization and loop closure detection for a mobile robot using visual saliency. The results in terms of accuracy and efficiency of localization and closure detection applications are evaluated and compared to the results obtained with the approaches provided in literature, both applied on different sequences of images acquired in outdoor environnement. The main drawback with the models proposed for the extraction of salient regions is their computational complexity, which leads to significant processing time. To obtain a real-time processing, we present in this thesis also the implementation of the salient region detector on the reconfigurable platform DreamCam
Saab, Christine. "Smart system for water quality control : feedback from large-scale experimentation." Thesis, Lille 1, 2018. http://www.theses.fr/2018LIL1I028/document.
Full textThis works presents the real-time control of drinking water quality using the smart technology. The deployment of water quality sensors in the distribution networks provides indication of contamination risks. However, the use of these innovative devices is recent and yet requires field experimentations. This thesis enhances the feedback in this domain. It presents a field study of online supervision of water quality, within SunRise project. This work is also a part of the European project “SmartWater4Europe”. The literature review highlights the impact of water contamination on human health as well as the drawbacks of conventional water supervision methods. A large-scale experimentation is conducted at the Scientific Campus of Lille University, where two types of sensors (S::CAN and EventLab) are implemented. The detailed analysis of recorded water quality signals showed the occurrence of some events, generally correlated with the variation of hydraulic parameters or the network interventions. Different methodologies for the detection of water anomaly are presented and applied to S::CAN data. Statistical and Artificial Intelligence (Support Vector Machine) methods discriminate between normal and unexpected measurements. An Event Detection System (EDS), developed within Canary software, showed a good performance in the identification of water abnormalities. The last part proposes a combination between the risk assessment approach and the smart monitoring. The improved risk assessment methodology allows a real-time detection and classification of water anomaly risk as well as an identification of the priority attention required
Li, Keli. "Etude et réalisation d'une plateforme reconfigurable et modulaire adaptée à la perception multisensorielle." Compiègne, 1997. http://www.theses.fr/1997COMP1077.
Full textThe work presented in this thesis consists of the study of the concept of active vision and multi-sensor perception, the realization of a modular reconfigurable platform adapted to the multi-sensor perception, and the implementation of the motion tracking algorithm. This work is also one part of the project “A parallel reconfigurable plat-form dedicated for omni-directional perception”. This work is divided into two parts. Firstly, we have dealt with the CIT plat-form architecture. A survey on the passive & active vision and the parallel architecture is presented in the beginning of the thesis. That allows to discover the problems in the existing computer vision systems for real-time task and to draw up a new vision system based on the concept of multi-sensor perception. To respect the general constraints : low consumption, low congestion, low cost and flexible, the plat-form permits to be inspired from some characteristics of the human vision to overcome the problems existing in the traditional system, to construct easily the DMIMD/SMIMD architectures. Consequently, it is able to carry out the vision tasks in real-time. Secondly, we have developed one application adapted to the CIT plat-form, that is the motion detection and tracking moving objet. In fact the current trend in optical flow research is to stress accuracy under ideal conditions and not to consider computational resource requirements or temporal constraint, which are essential for real-time tasks. As a result, practical applications for optical flow algorithms remain scarce. Algorithms based on the token matching and block matching have been shown to be fast in practice but are in general infeasible due to their severe environment requirement. This thesis has proposed a new algorithm CAES for active camera based on the energy detection algorithm. The experimental results show that it is robust, fast and precise for the motion detection and tracking. The algorithm will be implemented in a mono-chip VLSI by using the FPGA technology, which permits to execute it at video rate
Charfi, Imen. "Détection automatique de chutes de personnes basée sur des descripteurs spatio-temporels : définition de la méthode, évaluation des performances et implantation temps-réel." Phd thesis, Université de Bourgogne, 2013. http://tel.archives-ouvertes.fr/tel-00959850.
Full textGhemmogne, Fossi Leopold. "Gestion des règles basée sur l'indice de puissance pour la détection de fraude : Approches supervisées et semi-supervisées." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI079.
Full textThis thesis deals with the detection of credit card fraud. According to the European Central Bank, the value of frauds using cards in 2016 amounted to 1.8 billion euros. The challenge for institutions is to reduce these frauds. In general, fraud detection systems consist of an automatic system built with "if-then" rules that control all incoming transactions and trigger an alert if the transaction is considered suspicious. An expert group checks the alert and decides whether it is true or not. The criteria used in the selection of the rules that are kept operational are mainly based on the individual performance of the rules. This approach ignores the non-additivity of the rules. We propose a new approach using power indices. This approach assigns to the rules a normalized score that quantifies the influence of the rule on the overall performance of the group. The indexes we use are the Shapley Value and Banzhaf Value. Their applications are 1) Decision support to keep or delete a rule; 2) Selection of the number k of best-ranked rules, in order to work with a more compact set. Using real credit card fraud data, we show that: 1) This approach performs better than the one that evaluates the rules in isolation. 2) The performance of the set of rules can be achieved by keeping one-tenth of the rules. We observe that this application can be considered as a task of selection of characteristics: We show that our approach is comparable to the current algorithms of the selection of characteristics. It has an advantage in rule management because it assigns a standard score to each rule. This is not the case for most algorithms, which focus only on an overall solution. We propose a new version of Banzhaf Value, namely k-Banzhaf; which outperforms the previous in terms of computing time and has comparable performance. Finally, we implement a self-learning process to reinforce the learning in an automatic learning algorithm. We compare these with our power indices to rank credit card fraud data. In conclusion, we observe that the selection of characteristics based on the power indices has comparable results with the other algorithms in the self-learning process
Amri, Mohamed-Hédi. "Fusion ensembliste de donn´ees pour la surveillance des personnes d´ependantes en habitat intelligent." Thesis, Orléans, 2015. http://www.theses.fr/2015ORLE2030/document.
Full textOur research work is a part of the project FUI 14 FEDER Collectivités E-monitor’âge. This project takes place within the framework of Ambient Assisted Living (AAL) which aims to improve the safety and the comfort of elderly people living in smart nursing homes. This work aims to monitor the activities of elderly persons using information from different sensors. The ADL (Activities of Daily Living) are used to evaluate the ability of the person to perform on their own a selection of the activities which are essential for an independent living in the everyday life. Generally, process knowledge and measurements coming from sensors are prone to indeterminable noise. In our work, we suppose that these errors are unknown but bounded. Taking into account this hypothesis, we show how to solve the estimation issue using set-membership computations techniques. Our algorithm, based on set-membership approach, consists of two steps. The prediction step, based on the use of a random walk mobility with minimum assumptions (maximum speed of moving), employs the previous state estimate to provide the prediction zone where the person may be located. The correction step uses the informations coming from the sensors to refine this predicted zone. This step uses a relaxed constraints propagation technique, q-relaxed intersection, to deal with faulty measurements. This proposed method allows us to compute the uncertainty domain for the reconstructed localization of moving targets as dealing with outliers
Chabour, Ferhat. "Commande sans capteur de position d'une machine synchrone à rotor bobiné : application à l'alterno-démarreur séparé StARS." Compiègne, 2007. http://www.theses.fr/2007COMP1705.
Full textValeo Company produces for the automotive industry several synchronous machines intended to operate either in starter mode or in alternator mode. One of the manufactured machines is the Starter-Alternator Reversible System (StARS) that is a wound rotor belt-driven machine. Actually, StARS is supplied by a full-wave voltage inverter and its self-commutation is controlled by an integrated shaft-mounted position sensor. The removal of the latter is a very promising passage. In addition to the suppression of the costs due to the sensor and its installation, the elimination of the sensor's wiring improves the reliability and the robustness of the system. The main purpose of this thesis is to investigate the StARS sensorless control. At zero speed, initial rotor position detection and motor parameter identification are presented. In medium and high speed range, the sensorless operation of the StARS is based on the estimation of the machine rotational electromotive forces. At low speed, the rotor position is detected by estimating the stator flux which is obtained by integration of the measured back electromotive force. The proposed sensorless control can perform a switchover from starting to sensorless open-loop operation. It has a simple structure and uses two current sensors. Experimental results are presented to demonstrate the successful operation of the investigated sensorless method
Nasser, Abbass. "Spectrum sensing for half and full-duplex interweave cognitive radio systems." Thesis, Brest, 2017. http://www.theses.fr/2017BRES0006/document.
Full textDue to the increasing demand of wireless communication services and the limitation in the spectrum resources, Cognitive Radio (CR) has been initially proposed in order to solve the spectrum scarcity. CR divides the communication transceiver into two categories: the Primary (PU) or the Secondary (SU) Users. PU has the legal right to use the spectrum bandwidth, while SU is an opportunistic user that can transmit on that bandwidth whenever it is vacant in order to avoid any interference to the signal of PU. Hence the detection of PU becomes a main priority for CR systems. The Spectrum Sensing is the part of the CR system, which monitors the PU activities. Spectrum Sensing plays an essential role in the mechanism of the CR functioning. It provides CR with the available channel in order to access them, and on the other hand, it protects occupied channels from the interference of the SU transmission. In fact, Spectrum Sensing has gained a lot of attention in the last decade, and numerous algorithms are proposed to perform it. Concerning the reliability of the performance, several challenges have been addressed, such as the low Signal to Noise Ratio (SNR), the Noise Uncertainty (NU), the Spectrum Sensing duration, etc. This dissertation addresses the Spectrum Sensing challenges and some solutions are proposed. New detectors based on Cyclo-Stationary Features detection and the Power Spectral Density (PSD) of the PU are presented. CanonicalCorrelation Significance Test (CCST) algorithm is proposed to perform cyclo-stationary detection. CCST can detect the presence of the common cyclic features among the delayed versions of the received signal. This test can reveal the presence of a cyclo-stationary signal in the received mixture signal. Another detection method based on the cumulative PSD is proposed. By assuming the whiteness of the noise (its PSD is at), the cumulative PSD approaches a straight line. This shape becomes non-linear when a telecommunication signal is present in the received mixture. Distinguishing the Cumulative PSD shape may lead to diagnose the channel status.Full-Duplex Cognitive Radio (FD-CR) has been also studied in this manuscript, where several challenges are analyzed by proposing a new contribution. FD functioning permits CR to avoid the silence period during the Spectrum Sensing. In classical CR system, SU stops transmitting during the Spectrum Sensing in order to do not affect the detection reliability. In FD-CR, SU can eliminate the reflection of its transmitted signal and at the same time achieving the Spectrum Sensing. Due to some limitations, the residual of the Self Interference cannot be completely cancelled, then the Spectrum Sensing credibility is highly affected. In order to reduce the residual power, a new SU receiver architecture is worked out to mitigate the hardware imperfections (such as the Phase Noise and the Non-Linear Distortion of the receiver Low-Noise Amplifier). The new architecture shows its robustness by ensuring a reliable detection and enhancing the throughput of SU
Chen, Chao. "Understanding social and community dynamics from taxi GPS data." Phd thesis, Institut National des Télécommunications, 2014. http://tel.archives-ouvertes.fr/tel-01048662.
Full textRougier, Caroline. "Vidéosurveillance intelligente pour la détection de chutes chez les personnes âgées." Thèse, 2010. http://hdl.handle.net/1866/4113.
Full textDeveloped countries like Canada have to adapt to a growing population of seniors. A majority of seniors reside in private homes and most of them live alone, which can be dangerous in case of a fall, particularly if the person cannot call for help. Video surveillance is a new and promising solution for healthcare systems to ensure the safety of elderly people at home. Concretely, a camera network would be placed in the apartment of the person in order to automatically detect a fall. When a fall is detected, a message would be sent to the emergency center or to the family through a secure Internet connection. For a low cost system, we must limit the number of cameras to only one per room, which leads us to explore monocular methods for fall detection. We first studied 2D information (images) by analyzing the shape deformation during a fall. Normal activities of an elderly person were used to train a Gaussian Mixture Model (GMM) to detect any abnormal event. Our method was tested with a realistic video data set of simulated falls and normal activities. However, 3D information like the spatial localization of a person in a room can be very useful for action recognition. Although a multi-camera system is usually preferable to acquire 3D information, we have demonstrated that, with only one calibrated camera, it is possible to localize a person in his/her environment using the person’s head. Concretely, the head, modeled by a 3D ellipsoid, was tracked in the video sequence using particle filters. The precision of the 3D head localization was evaluated with a video data set containing the real 3D head localizations obtained with a Motion Capture system. An application example using the 3D head trajectory for fall detection is also proposed. In conclusion, we have confirmed that a video surveillance system for fall detection with only one camera per room is feasible. To reduce the risk of false alarms, a hybrid method combining 2D and 3D information could be considered.