<p>Foreground segmentation is a common first step in tracking and surveillance applications.  The purpose of foreground segmentation is to provide later stages of image processing with an indication of where interesting data can be found.  This thesis is an investigation of how foreground segmentation can be performed in two contexts: as a pre-step to trajectory tracking and as a pre-step in indoor surveillance applications.</p><p>Three methods are selected and detailed: a single Gaussian method, a Gaussian mixture model method, and a codebook method.  Experiments are then performed on typical input video using the methods.  It is concluded that the Gaussian mixture model produces the output which yields the best trajectories when used as input to the trajectory tracker.  An extension is proposed to the Gaussian mixture model which reduces shadow, improving the performance of foreground segmentation in the surveillance context.</p>

Ground penetrating radar (GPR) is a promising technique for humanitarian demining applications as it permits providing useful information about the subsurface based on wave reflections produced by electromagnetic (EM) contrasts. Yet, landmine detection using GPR can suffer from: (1) clutter, i.e, undesirable effects from antenna coupling, system ringing and soil surface and subsurface reflections; (2) false alarms, e.g., reflections from buried mine-like objects such as stones or metallic debris; (3) effects of soil properties on the GPR performance, such as attenuation. This thesis addresses these topics in an integrated approach aiming at reducing clutter, identifying landmines from false alarms and analysing GPR performance. For subtracting undesirable reflections, a new physically-based filtering algorithm is developed, which takes into account major antenna effects and soil surface reflection. It is applied in conjunction with a change detection algorithm for enhancing landmine detection. Landmine identification is performed using discriminant characteristics extracted from the pre-filtered data by a novel feature extraction approach in the time-frequency domain. For analysing the effects of soil properties, in particular soil dielectric permittivity, an EM model is coupled to pedotransfer functions for estimating the GPR performance on a given soil. The developed algorithms are validated using data acquired by two different hand-held GPR systems. Promising results are obtained under laboratory and outdoor conditions, where different types of soil (including real mine-affected soils) and landmines (including improvised explosive devices) are considered.

Ground penetrating radar (GPR) is a promising technique for humanitarian demining applications as it permits providing useful information about the subsurface based on wave reflections produced by electromagnetic (EM) contrasts. Yet, landmine detection using GPR can suffer from: (1) clutter, i.e, undesirable effects from antenna coupling, system ringing and soil surface and subsurface reflections; (2) false alarms, e.g., reflections from buried mine-like objects such as stones or metallic debris; (3) effects of soil properties on the GPR performance, such as attenuation. This thesis addresses these topics in an integrated approach aiming at reducing clutter, identifying landmines from false alarms and analysing GPR performance. For subtracting undesirable reflections, a new physically-based filtering algorithm is developed, which takes into account major antenna effects and soil surface reflection. It is applied in conjunction with a change detection algorithm for enhancing landmine detection. Landmine identification is performed using discriminant characteristics extracted from the pre-filtered data by a novel feature extraction approach in the time-frequency domain. For analysing the effects of soil properties, in particular soil dielectric permittivity, an EM model is coupled to pedotransfer functions for estimating the GPR performance on a given soil. The developed algorithms are validated using data acquired by two different hand-held GPR systems. Promising results are obtained under laboratory and outdoor conditions, where different types of soil (including real mine-affected soils) and landmines (including improvised explosive devices) are considered.

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

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

Background subtraction is the technique of segmenting moving foreground objects from stationary or dynamic background scenes. Background subtraction is a critical step in many computer vision applications including video surveillance, tracking, gesture recognition etc. This thesis addresses the challenges associated with the background subtraction systems due to the sudden illumination changes happening in an indoor environment. Most of the existing techniques adapt to gradual illumination changes, but fail to cope with the sudden illumination changes. Here, we introduce a Global change reactive background subtraction to model these changes as a regression function of spatial image coordinates. The regression model is learned from highly probable background regions and the background model is compensated for the illumination changes by the model parameters estimated. Experiments were performed in the indoor environment to show the effectiveness of our approach in modeling the sudden illumination changes by a higher order regression polynomial. The results of non-linear SVM regression were also presented to show the robustness of our regression model.

Background Subtraction is one of the fundamental pre-processing steps in video processing. It helps to distinguish between foreground and background for any given image and thus has numerous applications including security, privacy, surveillance and traffic monitoring to name a few. Unfortunately, no single algorithm exists that can handle various challenges associated with background subtraction such as illumination changes, dynamic background, camera jitter etc. In this work, we propose a Multiple Background Model based Background Subtraction (MB2S) system, which is universal in nature and is robust against real life challenges associated with background subtraction. It creates multiple background models of the scene followed by both pixel and frame based binary classification on both RGB and YCbCr color spaces. The masks generated after processing these input images are then combined in a framework to classify background and foreground pixels. Comprehensive evaluation of proposed approach on publicly available test sequences show superiority of our system over other state-of-the-art algorithms.

No description available.

Les travaux présentés dans ce manuscrit traitent de la détection de personnes dans des séquences d’images et de l’analyse de leur activité. Ces travaux ont été menés au sein de l’institut PRISME dans le cadre du projet CAPTHOM du pôle de compétitivité S2E2. Après un état de l’art sur l’analyse de séquences d’images pour l’interprétation automatique de scènes et une étude comparative de modules de vidéo-surveillance, nous présentons la méthode de détection de personnes proposée dans le cadre du projet CAPTHOM. Celle-ci s’articule autour de trois étapes : la détection de changement, le suivi d’objets mobiles et la classification. Chacune de ces étapes est décrite dans ce manuscrit. Ce système a été évalué sur une large base de vidéos correspondant à des scénarios de cas d’usage de CAPTHOM établis par les partenaires du projet. Ensuite, nous présentons des méthodes permettant d’obtenir, à partir du flux vidéo d’une ou deux caméras, d’autres informations de plus haut-niveau sur l’activité des personnes détectées. Nous présentons tout d’abord une mesure permettant de quantifier leur activité. Ensuite, un système de stéréovision multi-capteurs combinant une caméra infrarouge et une caméra visible est utilisé pour augmenter les performances du système de détection mais aussi pour permettre la localisation dans l’espace des personnes et donc accéder à une cartographie de leurs déplacements. Finalement, une méthode de détection d’événements anormaux, basée sur des statistiques de distributions spatiales et temporelles des pixels de l’avant-plan est détaillée. Les méthodes proposées offrent un panel de solutions performantes sur l’extraction d’informations haut-niveau à partir de séquences d’images. / The work presented in this manuscript deals with people detection and activity analysis in images sequences. This work has been done in the PRISME institut within the framework of the CAPTHOM project of the French Cluster S2E2. After a state of the art on video analysis and a comparative study of several video surveillance tools, we present the people detection method proposed within the framework of the CAPTHOM project. This method is based on three steps : change detection, mobile objects tracking and classification. Each steps is described in this thesis. The system was assessed on a wide videos dataset. Then, we present methods used to obtain other high-level information concerning the activity of detected persons. A criterion for characterizing their activity is presented. Then, a multi-sensors stereovision system combining an infrared and a daylight camera is used to increase performances of the people detection system but also to localize persons in the 3D space and so build the moving cartography. Finally, an abnormal events detection method based on statistics about spatio-temporal foreground pixel distribution is presented. These proposed methods offer robust and efficient solutions on high-level information extraction from images sequences.

Position of the vehicle is essential to navigate the vehicle along a desired path without any human interference. Global Positioning System (GPS) loses significant power due to signal attenuation caused by construction buildings. A good positioning system should have both good positioning accuracy and reliability. The purpose of this thesis is to implement a new positioning system using camera and examine the accuracy of the estimated vehicle position on a real-time scenario. The major focus of the thesis is to develop two algorithms for estimation of the position of the vehicle using a static camera and to evaluate the performance of the proposed algorithms. The proposed positioning system is based on two different processes. First process uses center of mass to estimate the position, while the second one utilizes gradient information to estimate the position of the vehicle. Two versions of the positioning systems are implemented. One version uses center of mass concept and background subtraction to estimate the position of the vehicle and the other version calculates gradients to estimate the position of the vehicle. Both algorithms are sensitive to point of view of the image i.e height of the camera. On comparing both algorithms, gradient based algorithm is less sensitive to the camera view. Finally, the performance is greater dependent on the height of the camera position for center of mass positioning system, as compared to the gradient positioning system but the accuracy of the systems can be improved by increasing the height of the camera. In terms of the speed of processing, the gradient positioning system is faster than the center of mass positioning system. The first algorithm, based on center of mass has 89.75\% accuracy with a standard deviation of 3 pixels and the second algorithm has an accuracy of 92.26\%. Accuracy of the system is estimated from the number of false detected positions.