Šiame darbe buvo ištirtas keleto pasirinktų objekto vaizde sekimo metodų pritaikomumas relaus laiko vaizdo transliavimo sistemose. Išsiaiškinta, kad standartinis blokelių sutapdinimo algoritmas, nors yra pats paprasčiausias iš tirtųjų, yra netinkamas naudoti tokiose sistemose dėl ilgai užtrunkančių skaičiavimų, kurie sukuria papildomą vaizdo vėlinimą. Fazinės koreliacijos metodo taikymo taip pat buvo atsisakyta, nes jo randami vaizdo poslinkio vektoriai yra pernelyg atsitiktiniai. Tiriant būdingųjų taškų paieška ir sutapdinimu grįstus algoritmus buvo išsiaiškinta, kad HARRIS randa daugiausiai taškų iš visų, FAST algoritmas veikia greičiausiai, nors randamų taškų skaičius ir tikslumas yra žymiai mažesnis, o SURF ir MSER algoritmai puikiai balansuoja tarp randamų taškų skaičiaus, jų tikslumo ir skaičiavimų vykdymo greičio. Padarėme išvadas, kad visi tirti būdingųjų taškų sutapdinimu ir paieška pagrįsti metodai, priklausomai nuo uždavinio pobūdžio, gali būti taikomi realaus laiko vaizdo transliacijos sistemos objektams vaizde sekti. / In this thesis we've investigated methods used in object tracking in video sequences, that could be applied in systems of real-time video streaming. We've found out that a standard block matching method, despite being the most simplistic one out of all methods investigated, is also the most time consuming and cannot be applied in real-time systems. Phase correlation method is much faster than block matching, but motion vectors calculated with this algorithm are too random and it would be impractical to use it in real-time object tracking. While investigating feature detection and matching methods we've concluded that HARRIS algorithm finds more feature points than others, FAST algorithm is the fastest, but not very accurate, SURF and MSER algorithms retains the balance between the calculation speed and accuracy of finding feature points. Hence all these algorithms could be applied in real-time video streaming systems to track objects, depending on the contents of the video sequence and the complexity of the task.

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 trafic. / Automatic 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.

The popularization of social media, combined with the widespread use of smartphones and the use of advanced equipment in hospitals and medical centers has generated single and sequences of complex data, including images of high quality and in large quantity. Providing appropriate tools to extract meaningful knowledge from such data is a big challenge, and taking advantage of existing approaches to find patterns from images can be meaningful. While many potential techniques have been proposed to analyze images, most of the processing performed by image mining techniques consider the entire image. Thus, regions that are not of interest are considered in the analysis step, without proper distinction and consequently damaging most tasks. This doctorate PhD research has the following thesis: The analysis of image regions, combined to additional information, leads to more accurate mining results regarding the entire image, and also helps the processing of sequences of images, speeding-up costly pipelines and making it possible to infer knowledge from objects movement. We evaluate this thesis in three application scenarios. In the first scenario, we analyzed regions of images from emergency situations, gathered from social media and which depict smoke regions. We were able to segment smoke regions and improve the classification of smoke images by up to 23%, compared to global approaches. In the second scenario, we worked with images from the medical context, containing Interstitial Lung Diseases (ILD). We classified the images considering the uncertainty of each lung region to contain different abnormalities, representing the obtained results with a heat map visualization. Our approach was able to outperform its competitors in the classification of lung regions by up to four of five classes of abnormalities. In the third scenario, we dealt with sequences of microscopic images depicting embryos being developed over time. Using region-based information of images, we were able to track and predict cells over time and build their motion vector. Our approaches showed an improvement of up to 57% in quality, and a speed-up of the tracking pipeline by up to 81:9%. Therefore, this PhD research contributed to the state-of-the-art by introducing methods of region-based image analysis for the three aforementioned application scenarios. / A popularização de redes sociais e o uso generalizado de smartphones e equipamentos avançados em hospitais têm gerado dados complexos e sequências de dados, tais como imagens de alta qualidade, em grande quantidade. Fornecer ferramentas apropriadas para extrair conhecimento útil de tais dados é um grande desafio, e tirar vantagem de abordagens existentes para encontrar padrões em imagens pode ser significativo. Enquanto diversas técnicas em potencial têm sido propostas para analisar imagens, grande parte dessas técnicas consideram a imagem inteira na análise. Assim, regiões que não são de interesse são consideradas na etapa de análise, sem distinção apropriada e consequentemente prejudicando diversas tarefas. Esta pesquisa de Doutorado baseou-se na seguinte tese: A análise de regiões de imagens, combinada com informações adicionais, leva a resultados de mineração mais precisos em relação à imagem inteira, ajudando também no processamento de sequências de imagens, acelerando pipelines custosos e tornando possível inferir conhecimento do movimento de objetos. Essa tese foi avaliada em três cenários de aplicação. No primeiro cenário, foram analisadas regiões de imagens de situações de emergência, obtidas por meio de redes sociais e que apresentavam regiões de fumaça. Os métodos propostos são capazes de segmentar regiões de fumaça e melhorar a classificação global de imagens em até 23% em comparação ao estado da arte. No segundo cenário, foram abordadas imagens do contexto médico, contendo doenças pulmonares intersticiais. As imagens foram classificadas considerando a incerteza de cada região do pulmão em conter diferentes anormalidades, representando os resultados obtidos por meio de uma visualização baseada em mapas de calor. A abordagem proposta foi melhor que os competidores na tarefa de classificação de regiões pulmonares, apresentando melhores resultados em até quatro de cinco anormalidades. No terceiro cenário, foram tratadas de sequências de imagens microscópicas, exibindo embriões se desenvolvendo ao longo do tempo. Com o uso de informações das imagens baseadas em regiões, foi possível rastrear e predizer trajetórias de células ao longo do tempo, e também construir o vetor de movimento das mesmas. As abordagens propostas mostraram uma melhora de até 57% em qualidade, e uma melhora de tempo no pipeline de rastreamento de até 81:9%. Esta tese de Doutorado contribuiu para o estado da arte introduzindo métodos de análise de imagem baseados em região para os três cenários de aplicação mencionados anteriormente.

Les systèmes de surveillance modernes doivent coordonner leurs stratégies d’observation pour améliorer l’information obtenue lors de leurs futures mesures afin d’estimer avec précision les états des objets d’intérêt (emplacement, vitesse, apparence, etc.). Par conséquent, la gestion adaptative des capteurs consiste à déterminer les stratégies de mesure des capteurs exploitant les informations a priori afin de déterminer les actions de détection actuelles. L’une des applications la plus connue de la gestion des capteurs est le suivi multi-objet, qui fait référence au problème de l’estimation conjointe du nombre d’objets et de leurs états ou trajectoires à partir de mesures bruyantes. Cette thèse porte sur les stratégies de gestion des capteurs en temps réel afin de résoudre le problème du suivi multi-objet dans le cadre de l’approche RFS labélisée. La première contribution est la formulation théorique rigoureuse du filtre mono-capteur LPHD avec son implémentation Gaussienne. La seconde contribution est l’extension du filtre LPHD pour le cas multi-capteurs. La troisième contribution est le développement de la méthode de gestion de capteurs basée sur la minimisation du risque Bayes et formulée dans les cadres POMDP et LRFS. En outre, des analyses et des simulations des approches de gestion de capteurs existantes pour le suivi multi-objets sont fournies / Modern surveillance systems must coordinate their observation strategies to enhance the information obtained by their future measurements in order to accurately estimate the states of objects of interest (location, velocity, appearance, etc). Therefore, adaptive sensor management consists of determining sensor measurement strategies that exploit a priori information in order to determine current sensing actions. One of the most challenging applications of sensor management is the multi-object tracking, which refers to the problem of jointly estimating the number of objects and their states or trajectories from noisy sensor measurements. This thesis focuses on real-time sensor management strategies formulated in the POMDP framework to address the multi-object tracking problem within the LRFS approach. The first key contribution is the rigorous theoretical formulation of the mono-sensor LPHD filter with its Gaussian-mixture implementation. The second contribution is the extension of the mono-sensor LPHD filter for superpositional sensors, resulting in the theoretical formulation of the multi-sensor LPHD filter. The third contribution is the development of the Expected Risk Reduction (ERR) sensor management method based on the minimization of the Bayes risk and formulated in the POMDP and LRFS framework. Additionally, analyses and simulations of the existing sensor management approaches for multi-object tracking, such as Task-based, Information-theoretic, and Risk-based sensor management, are provided.

Les travaux présentés dans cette thèse concernent le thème des fonctionnalités visuelles qu'il convient d'embarquer sur un robot mobile, afin qu'il puisse se déplacer dans son environnement. Plus précisément, ils ont trait aux méthodes de perception par vision stéréoscopique dense, de modélisation de l'environnement par grille d'occupation, et de suivi visuel d'objets, pour la navigation autonome d'un robot mobile dans un environnement d'intérieur. Il nous semble important que les méthodes de perception visuelle soient à la fois robustes et rapide. Alors que dans les travaux réalisés, on trouve les méthodes globales de mise en correspondance qui sont connues pour leur robustesse mais moins pour être employées dans les applications temps réel et les méthodes locales qui sont les plus adaptées au temps réel tout en manquant de précision. Pour cela, ce travail essaye de trouver un compromis entre robustesse et temps réel en présentant une méthode semi-locale, qui repose sur la définition des distributions de possibilités basées sur une formalisation floue des contraintes stéréoscopiques.Il nous semble aussi important qu'un robot puisse modéliser au mieux son environnement. Une modélisation fidèle à la réalité doit prendre en compte l'imprécision et l'incertitude. Ce travail présente une modélisation de l'environnement par grille d'occupation qui repose sur l'imprécision du capteur stéréoscopique. La mise à jour du modèle est basée aussi sur la définition de valeurs de crédibilité pour les mesures prises.Enfin, la perception et la modélisation de l'environnement ne sont pas des buts en soi mais des outils pour le robot pour assurer des tâches de haut niveau. Ce travail traite du suivi visuel d'un objet mobile comme tâche de haut niveau. / This work concerns visual functionalities to be embedded in a mobile robot for navigation purposes. More specifically, it relates to methods of dense stereoscopic vision based perception, grid occupancy based environment modeling and object tracking for autonomous navigation of mobile robots in indoor environments.We consider that is important for visual perception methods to be robust and fast. While in previous works, there are global stereo matching methods which are known for their robustness, but less likely to be employed in real-time applications. There are also local methods which are more suitable for real time but imprecise. To this aim, this work tries to find a compromise between robustness and real-time by proposing a semi-local method based on the definition of possibility distributions built around a fuzzy formalization of stereoscopic constraints.We consider also important for a mobile robot to better model its environment. To better fit a model to the reality we have to take uncertainty and inaccuracy into account. This work presents an occupancy grid environment modeling based on stereoscopic sensor inaccuracy.. Model updating relies on the definition of credibility values for the measures taken.Finally, perception and environment modeling are not goals but tools to provide robot high-level tasks. This work deals with visual tracking of a moving object such as high-level task.

Made available in DSpace on 2015-03-05T14:01:20Z (GMT). No. of bitstreams: 0 Previous issue date: 13 / Nenhuma / O baixo custo dos sistemas de aquisição de imagens e o aumento no poder computacional das máquinas disponíveis têm causado uma demanda crescente pela análise automatizada de vídeo, em diversas aplicações, como segurança, interfaces homem-computador, análise de desempenho esportivo, etc. O rastreamento de objetos através de câmeras de vídeo é parte desta análise, e tem-se mostrado um problema desafiador na área de visão computacional. Este trabalho apresenta uma nova abordagem para o rastreamento de objetos baseada em fragmentos. Inicialmente, a região selecionada para o rastreamento é dividida em sub-regiões retangulares (fragmentos), e cada fragmento é rastreado independentemente. Além disso, o histórico de movimentação do objeto é utilizado para estimar sua posição no quadro seguinte. O deslocamento global do objeto é então obtido combinando os deslocamentos de cada fragmento e o deslocamento previsto, de modo a priorizar fragmentos com deslocamento coerente. Um esquema de atualização é aplicado no modelo / The low cost of image acquisition systems and increase the computational power of available machines have caused a growing demand for automated video analysis in several applications, such as surveillance, human-computer interfaces, analysis of sports performance, etc. Object tracking through the video sequence is part of this analysis, and it has been a challenging problem in the computer vision area. This work presents a new approach for object tracking based on fragments. Initially, the region selected for tracking is divided into rectangular subregions (patches, or fragments), and each patch is tracked independently. Moreover, the motion history of the object is used to estimate its position in the subsequent frames. The overall displacement of the object is then obtained combining the displacements of each patch and the predicted displacement vector in order to priorize fragments presenting consistent displacement. An update scheme is also applied to the model, to deal with illumination and appearance c

Diversos problemas práticos envolvendo sistemas de visão computacional, tais como vigilância automatizada, pesquisas de conteúdo específico em bancos de dados multimídias ou edição de vídeo, requerem a localização e o reconhecimento de objetos dentro de seqüências de imagens ou vídeos digitais. Mais formalmente, denomina-se rastreamento o processo de determinação da posição de certo(s) objeto(s) ao longo do tempo numa seqüência de imagens. Já a tarefa de reconhecimento caracteriza-se pela classificação desses objetos de acordo com algum rótulo pré-estabelecido ou apoiada em conhecimento prévio tipicamente introduzido através de um modelo dos objetos de interesse. No entanto, rastrear e classificar objetos em vídeo digital são tarefas desafiadoras, tanto pelas dificuldades inerentes a esse tipo de elemento pictórico, quanto pelo variável grau de complexidade que os quadros sob análise podem apresentar. Este documento apresenta uma metodologia baseada em modelo para rastrear e reconhecer objetos em vídeo digital através de uma representação por grafos relacionais com atributos (ARGs). Tais estruturas surgiram dentro do paradigma de reconhecimento estrutural de padrões e têm se mostrado bastante flexíveis e poderosas para modelar problemas diversos, pois podem transmitir dados quantitativos, relacionais, estruturais e simbólicos. Como modelo e entrada são descritos através desses grafos, a questão de reconhecimento é interpretada como um problema de casamento inexato entre grafos, que consiste em mapear os vértices do ARG de entrada nos vértices do ARG modelo. Em seguida, é realizado o rastreamento dos objetos de acordo com uma transformação afim derivada de parâmetros obtidos da etapa de reconhecimento. Para validar a metodologia proposta, resultados sobre seqüências de imagens digitais, sintéticas e reais, são apresentados e discutidos. / Several practical problems involving computer vision systems, such as automated surveillance, content-based queries in multimedia databases or video editing require the location and recognition of objects within image sequences or digital video. More formally, the process of determining the position of certain objects in an image sequence throughout time is called tracking, whereas the recognition task is characterized by the classification of such objects according to pre-defined labels or a priori knowledge, typically introduced by means of a model of the target objects. However, tracking and recognition of objects in digital video are not simple tasks, either because of the inherent difficulties of such a pictorial element, or due to the variable level of complexity that the frames under consideration might present. This document presents a model-based methodology for tracking and recognizing objects represented by attributed relational graphs (ARGs) in digital video. These structures have arisen from the paradigm of structural pattern recognition and have proven to be very flexible and powerful for modeling various problems, as they can hold many sorts of data (e.g: quantitative, relational, structural and symbolic). Since both model and input data are described through these graphs, the recognition matter may be interpreted as an inexact graph matching problem, which consists in finding a correspondence between the set of vertices of the input ARG and that of the model ARG. In the next step, object tracking is performed according to an affine transform derived from parameters extracted from the recognition phase. To validate the proposed methodology, results obtained from real and synthetic digital image sequences are presented and discussed.

Emergency landing is a critical safety mechanism for aerial vehicles. Commercial aircraft have triply-redundant systems that greatly increase the probability that the pilot will be able to land the aircraft at a designated airfield in the event of an emergency. In general aviation, the chances of always reaching a designated airfield are lower, but the successful pilot might use landmarks and other visual information to safely land in unprepared locations. For small unmanned aircraft systems (sUAS), triply- or even doubly-redundant systems are unlikely due to size, weight, and power constraints. Additionally, there is a growing demand for beyond visual line of sight (BVLOS) operations, where an sUAS operator would be unable to guide the vehicle safely to the ground. This thesis presents a machine vision-based approach to emergency landing for small unmanned aircraft systems. In the event of an emergency, the vehicle uses a pre-compiled database of potential landing sites to select the most accessible location to land based on vehicle health. Because it is impossible to know the current state of any ground environment, a camera is used for real-time visual feedback. Using the recently developed Recursive-RANSAC algorithm, an arbitrary number of moving ground obstacles can be visually detected and tracked. If obstacles are present in the selected ditch site, the emergency landing system chooses a new ditch site to mitigate risk. This system is called Safe2Ditch.

La perception de scènes routières est un domaine de recherche très actif. Cette thèse se focalise sur la détection et le suivi d’objets par fusion de données d’un système multi-capteurs composé d’un télémètre laser, une caméra fisheye et un système de positionnement global (GPS). Plusieurs étapes de la chaîne de perception sont ´ étudiées : le calibrage extrinsèque du couple caméra fisheye / télémètre laser, la détection de la route et enfin la détection et le suivi d’obstacles sur la route.Afin de traiter les informations géométriques du télémètre laser et de la caméra fisheye dans un repère commun, une nouvelle approche de calibrage extrinsèque entre les deux capteurs est proposée. La caméra fisheye est d’abord calibrée intrinsèquement. Pour cela, trois modèles de la littérature sont étudiés et comparés. Ensuite, pour le calibrage extrinsèque entre les capteurs,la normale au plan du télémètre laser est estimée par une approche de RANSAC couplée `a une régression linéaire `a partir de points connus dans le repère des deux capteurs. Enfin une méthode des moindres carres basée sur des contraintes géométriques entre les points connus, la normale au plan et les données du télémètre laser permet de calculer les paramètres extrinsèques. La méthode proposée est testée et évaluée en simulation et sur des données réelles.On s’intéresse ensuite `a la détection de la route à partir des données issues de la caméra fisheye et du télémètre laser. La détection de la route est initialisée `a partir du calcul de l’image invariante aux conditions d’illumination basée sur l’espace log-chromatique. Un seuillage sur l’histogramme normalisé est appliqué pour classifier les pixels de la route. Ensuite, la cohérence de la détection de la route est vérifiée en utilisant les mesures du télémètre laser. La segmentation de la route est enfin affinée en exploitant deux détections de la route successives. Pour cela, une carte de distance est calculée dans l’espace couleur HSI (Hue,Saturation, Intensity). La méthode est expérimentée sur des données réelles. Une méthode de détection d’obstacles basée sur les données de la caméra fisheye, du télémètre laser, d’un GPS et d’une cartographie routière est ensuite proposée. On s’intéresse notamment aux objets mobiles apparaissant flous dans l’image fisheye. Les régions d’intérêts de l’image sont extraites `a partir de la méthode de détection de la route proposée précédemment. Puis, la détection dans l’image du marquage de la ligne centrale de la route est mise en correspondance avec un modelé de route reconstruit `a partir des données GPS et cartographiques. Pour cela, la transformation IPM (Inverse Perspective Mapping) est appliquée à l’image. Les régions contenant potentiellement des obstacles sont alors extraites puis confirmées à l’aide du télémètre laser.L’approche est testée sur des données réelles et comparée `a deux méthodes de la littérature. Enfin, la dernière problématique étudiée est le suivi temporel des obstacles détectés `a l’aide de l’utilisation conjointe des données de la caméra fisheye et du télémètre laser. Pour cela, les resultats de détection d’obstacles précédemment obtenus sont exploit ´es ainsi qu’une approche de croissance de région. La méthode proposée est également testée sur des données réelles. / Road scene understanding is one of key research topics of intelligent vehicles. This thesis focuses on detection and tracking of obstacles by multisensors data fusion and analysis. The considered system is composed of a lidar, a fisheye camera and aglobal positioning system (GPS). Several steps of the perception scheme are studied: extrinsic calibration between fisheye camera and lidar, road detection and obstacles detection and tracking. Firstly, a new method for extinsic calibration between fisheye camera and lidar is proposed. For intrinsic modeling of the fisheye camera, three models of the literatureare studied and compared. For extrinsic calibration between the two sensors, the normal to the lidar plane is firstly estimated based on the determination of ń known ż points. The extrinsic parameters are then computed using a least square approachbased on geometrical constraints, the lidar plane normal and the lidar measurements. The second part of this thesis is dedicated to road detection exploiting both fisheye camera and lidar data. The road is firstly coarse detected considering the illumination invariant image. Then the normalised histogram based classification is validated using the lidar data. The road segmentation is finally refined exploiting two successive roaddetection results and distance map computed in HSI color space. The third step focuses on obstacles detection, especially in case of motion blur. The proposed method combines previously detected road, map, GPS and lidar information.Regions of interest are extracted from previously road detection. Then road central lines are extracted from the image and matched with road shape model extracted from 2DŋSIG map. Lidar measurements are used to validated the results.The final step is object tracking still using fisheye camera and lidar. The proposed method is based on previously detected obstacles and a region growth approach. All the methods proposed in this thesis are tested, evaluated and compared to stateŋofŋtheŋart approaches using real data acquired with the IRTESŋSET laboratory experimental platform.

This thesis presents new approaches to image registration and super-resolution mosaicing as well as their applications. Firstly, a feature-based image registration method is proposed for a multisensor surveillance system that consists of an optical camera and an infrared camera. By integrating a non-rigid object tracking technique into this method, a novel approach to simultaneous object tracking and multisensor image registration is proposed. Based on the registration and fusion of multisensor information, automatic face detection is greatly improved. Secondly, some extensions of a gradient-based image registration method, called inverse compositional algorithm, are proposed. These extensions include cumulative multi-image registration and the incorporation of illumination change and lens distortion correction. They are incorporated into the framework of the original algorithm in a consistent manner and efficiency can still be achieved for multi-image registration with illumination and lens distortion correction. Thirdly, new super-resolution mosaicing algorithms are proposed for multiple uncompressed and compressed images. Considering the process of image formation, observation models are introduced to describe the relationship between the superresolution mosaic image and the uncompressed and compressed low-resolution images. To improve the performance of super-resolution mosaicing, a wavelet-based image interpolation technique and an approach to adaptive determination of the regularization parameter are presented. For compressed images, a spatial-domain algorithm and a transform-domain algorithm are proposed. All the proposed superresolution mosaicing algorithms are robust against outliers. They can produce superresolution mosaics and reconstructed super-resolution images with improved subjective quality. Finally, new techniques for super-resolution sprite generation and super-resolution sprite coding are proposed. Considering both short-term and long-term motion influences, an object-based image registration method is proposed for handling long image sequences. In order to remove the influence of outliers, a robust technique for super-resolution sprite generation is presented. This technique produces sprite images and reconstructed super-resolution images with high visual quality. Moreover, it provides better reconstructed low-resolution images compared with low-resolution sprite generation techniques. Due to the advantages of the super-resolution sprite, a super-resolution sprite coding technique is also proposed. It achieves high coding efficiency especially at a low bit-rate and produces both decoded low-resolution and super-resolution images with improved subjective quality. Throughout this work, the performance of all the proposed algorithms is evaluated using both synthetic and real image sequences.