<p> In this thesis the problem of object recognition/pose estimation using active sensing is investigated. It is assumed that multiple cameras acquire images from different view angles of an object belonging to a set of a priori known objects. The eigenspace method is used to process the sensory observations and produce an abstract measurement vector. This step is necessary to avoid the manipulation of the original sensor data, i.e. large images, that can render the sensor modelling and matching process practically infeasible.</p> <p> The eigenspace representation is known to have shortcomings in dealing with structured noise such as occlusion. To overcome this problem, models of occlusions and sensor noise have been incorporated into the probabilistic model of sensor/object to increase robustness with respect to such uncertainties. The active recognition algorithm has also been modified to consider the possibility of occlusion, as well as variation in the occlusion levels due to camera movements.</p> <p> A recursive Bayesian state estimation problem is formulated to model the observation uncertainties through a probabilistic scheme. This enables us to identify the object and estimate its pose by fusing the information obtained from individual cameras. To this end, an extensive training step is performed, providing the system with the sensor model required for the Bayesian estimation. In order to enhance the quality of the estimates and to reduce the number of images taken, we employ active real-time viewpoint planning strategies to position cameras. For that purpose, the positions of cameras are controlled based on two different statistical performance criteria, namely the Mutual Information (MI) and Cramér-Rao Lower Bound (CRLB).</p> <p> A multi-camera active vision system has been developed in order to implement the ideas proposed in this thesis. Comparative Monte Carlo experiments conducted with the two-camera system demonstrate the effectiveness of the proposed methods in object classification/pose estimation in the presence of structured noise. Different concepts introduced in this work, i.e., the multi-camera data fusion, the occlusion modelling, and the active camera movement, all improve the recognition process significantly. Specifically, these approaches all increase the recognition rate, decrease the number of steps taken before recognition is completed, and enhance robustness with respect to partial occlusion considerably.</p> / Thesis / Master of Applied Science (MASc)

In this dissertation, we present vision based scene interpretation methods for monitoring of people and vehicles, in real-time, within a busy environment using a forest of co-operative electro-optical (EO) sensors. We have developed novel video understanding algorithms with learning capability, to detect and categorize people and vehicles, track them with in a camera and hand-off this information across multiple networked cameras for multi-camera tracking. The ability to learn prevents the need for extensive manual intervention, site models and camera calibration, and provides adaptability to changing environmental conditions. For object detection and categorization in the video stream, a two step detection procedure is used. First, regions of interest are determined using a novel hierarchical background subtraction algorithm that uses color and gradient information for interest region detection. Second, objects are located and classified from within these regions using a weakly supervised learning mechanism based on co-training that employs motion and appearance features. The main contribution of this approach is that it is an online procedure in which separate views (features) of the data are used for co-training, while the combined view (all features) is used to make classification decisions in a single boosted framework. The advantage of this approach is that it requires only a few initial training samples and can automatically adjust its parameters online to improve the detection and classification performance. Once objects are detected and classified they are tracked in individual cameras. Single camera tracking is performed using a voting based approach that utilizes color and shape cues to establish correspondence in individual cameras. The tracker has the capability to handle multiple occluded objects. Next, the objects are tracked across a forest of cameras with non-overlapping views. This is a hard problem because of two reasons. First, the observations of an object are often widely separated in time and space when viewed from non-overlapping cameras. Secondly, the appearance of an object in one camera view might be very different from its appearance in another camera view due to the differences in illumination, pose and camera properties. To deal with the first problem, the system learns the inter-camera relationships to constrain track correspondences. These relationships are learned in the form of multivariate probability density of space-time variables (object entry and exit locations, velocities, and inter-camera transition times) using Parzen windows. To handle the appearance change of an object as it moves from one camera to another, we show that all color transfer functions from a given camera to another camera lie in a low dimensional subspace. The tracking algorithm learns this subspace by using probabilistic principal component analysis and uses it for appearance matching. The proposed system learns the camera topology and subspace of inter-camera color transfer functions during a training phase. Once the training is complete, correspondences are assigned using the maximum a posteriori (MAP) estimation framework using both the location and appearance cues. Extensive experiments and deployment of this system in realistic scenarios has demonstrated the robustness of the proposed methods. The proposed system was able to detect and classify targets, and seamlessly tracked them across multiple cameras. It also generated a summary in terms of key frames and textual description of trajectories to a monitoring officer for final analysis and response decision. This level of interpretation was the goal of our research effort, and we believe that it is a significant step forward in the development of intelligent systems that can deal with the complexities of real world scenarios.

The purpose of this project is to implement, analyze and compare visual odometry approaches to help the localization task in autonomous vehicles. The stereo visual odometry algorithm Libviso2 is compared with a proposed omnidirectional multi-camera approach. The proposed method consists of performing monocular visual odometry on all cameras individually and selecting the best estimate through a voting scheme involving all cameras. The omnidirectionality of the vision system allows the part of the surroundings richest in features to be used in the relative pose estimation. Experiments are carried out using cameras Bumblebee XB3 and Ladybug 2, fixed on the roof of a vehicle. The voting process of the proposed omnidirectional multi-camera method leads to some improvements relatively to the individual monocular estimates. However, stereo visual odometry provides considerably more accurate results. / O objetivo deste mestrado é implementar, analisar e comparar abordagens de odometria visual, de forma a contribuir para a localização de um veículo autônomo. O algoritmo de odometria visual estéreo Libviso2 é comparado com um método proposto, que usa um sistema multi-câmera omnidirecional. De acordo com este método, odometria visual monocular é calculada para cada câmera individualmente e, seguidamente, a melhor estimativa é selecionada através de um processo de votação que involve todas as câmeras. O fato de o sistema de visão ser omnidirecional faz com que a parte dos arredores mais rica em características possa sempre ser usada para estimar a pose relativa do veículo. Nas experiências são utilizadas as câmeras Bumblebee XB3 e Ladybug 2, fixadas no teto de um veículo. O processo de votação do método multi-câmera omnidirecional proposto apresenta melhorias relativamente às estimativas monoculares individuais. No entanto, a odometria visual estéreo fornece resultados mais precisos.

"Patient motion, which causes artifacts in reconstructed images, can be a serious problem in Single Photon Emission Computed Tomography (SPECT) imaging. If patient motion can be detected and quantified, the reconstruction algorithm can compensate for the motion. A real-time multi-threaded Visual Tracking System (VTS) using optical cameras, which will be suitable for deployment in clinical trials, is under development. The VTS tracks patients using multiple video images and image processing techniques, calculating patient motion in three-dimensional space. This research aimed to develop and implement an algorithm for feature matching and stereo location computation using multiple cameras. Feature matching is done based on the epipolar geometry constraints for a pair of images and extended to the multiple view case with an iterative algorithm. Stereo locations of the matches are then computed using sum of squared distances from the projected 3D lines in SPECT coordinates as the error metric. This information from the VTS, when coupled with motion assessment from the emission data itself, can provide a robust compensation for patient motion as part of reconstruction."

The purpose of this project is to implement, analyze and compare visual odometry approaches to help the localization task in autonomous vehicles. The stereo visual odometry algorithm Libviso2 is compared with a proposed omnidirectional multi-camera approach. The proposed method consists of performing monocular visual odometry on all cameras individually and selecting the best estimate through a voting scheme involving all cameras. The omnidirectionality of the vision system allows the part of the surroundings richest in features to be used in the relative pose estimation. Experiments are carried out using cameras Bumblebee XB3 and Ladybug 2, fixed on the roof of a vehicle. The voting process of the proposed omnidirectional multi-camera method leads to some improvements relatively to the individual monocular estimates. However, stereo visual odometry provides considerably more accurate results. / O objetivo deste mestrado é implementar, analisar e comparar abordagens de odometria visual, de forma a contribuir para a localização de um veículo autônomo. O algoritmo de odometria visual estéreo Libviso2 é comparado com um método proposto, que usa um sistema multi-câmera omnidirecional. De acordo com este método, odometria visual monocular é calculada para cada câmera individualmente e, seguidamente, a melhor estimativa é selecionada através de um processo de votação que involve todas as câmeras. O fato de o sistema de visão ser omnidirecional faz com que a parte dos arredores mais rica em características possa sempre ser usada para estimar a pose relativa do veículo. Nas experiências são utilizadas as câmeras Bumblebee XB3 e Ladybug 2, fixadas no teto de um veículo. O processo de votação do método multi-câmera omnidirecional proposto apresenta melhorias relativamente às estimativas monoculares individuais. No entanto, a odometria visual estéreo fornece resultados mais precisos.

Réalisé en cotutelle avec le laboratoire M2S de Rennes 2 / Cette thèse s’intéresse à définir de nouvelles méthodes cliniques d’investigation permettant de juger de l’impact de l’avance en âge sur la motricité. En particulier, cette thèse se focalise sur deux principales perturbations possibles lors de l’avance en âge : la chute et l’altération de la marche.Ces deux perturbations motrices restent encore mal connues et leur analyse en clinique pose de véritables défis technologiques et scientifiques. Dans cette thèse, nous proposons des méthodes originales de détection qui peuvent être utilisées dans la vie courante ou en clinique, avec un minimum de contraintes techniques. Dans une première partie, nous abordons le problème de la détection de la chute à domicile, qui a été largement traité dans les années précédentes. En particulier, nous proposons une approche permettant d’exploiter le volume du sujet, reconstruit à partir de plusieurs caméras calibrées. Ces méthodes sont généralement très sensibles aux occultations qui interviennent inévitablement dans le domicile et nous proposons donc une approche originale beaucoup plus robuste à ces occultations. L’efficacité et le fonctionnement en temps réel ont été validés sur plus d’une vingtaine de vidéos de chutes et de leurres, avec des résultats approchant les 100% de sensibilité et de spécificité en utilisant 4 caméras ou plus. Dans une deuxième partie, nous allons un peu plus loin dans l’exploitation des volumes reconstruits d’une personne, lors d’une tâche motrice particulière : la marche sur tapis roulant, dans un cadre de diagnostic clinique. Dans cette partie, nous analysons plus particulièrement la qualité de la marche. Pour cela nous développons le concept d’utilisation de caméras de profondeur pour la quantification de l’asymétrie spatiale au cours du mouvement des membres inférieurs pendant la marche. Après avoir détecté chaque pas dans le temps, cette méthode réalise une comparaison de surfaces de chaque jambe avec sa correspondante symétrique du pas opposé. La validation effectuée sur une cohorte de 20 sujets montre la viabilité de la démarche. / This thesis is concerned with defining new clinical investigation method to assess the impact of ageing on motricity. In particular, this thesis focuses on two main possible disturbance during ageing : the fall and walk impairment. This two motricity disturbances still remain unclear and their clinical analysis presents real scientist and technological challenges. In this thesis, we propose novel measuring methods usable in everyday life or in the walking clinic, with a minimum of technical constraints. In the first part, we address the problem of fall detection at home, which was widely discussed in previous years. In particular, we propose an approach to exploit the subject’s volume, reconstructed from multiple calibrated cameras. These methods are generally very sensitive to occlusions that inevitably occur in the home and we therefore propose an original approach much more robust to these occultations. The efficiency and real-time operation has been validated on more than two dozen videos of falls and lures, with results approaching 100 % sensitivity and specificity with at least four or more cameras. In the second part, we go a little further in the exploitation of reconstructed volumes of a person at a particular motor task : the treadmill, in a clinical diagnostic. In this section we analyze more specifically the quality of walking. For this we develop the concept of using depth camera for the quantification of the spatial and temporal asymmetry of lower limb movement during walking. After detecting each step in time, this method makes a comparison of surfaces of each leg with its corresponding symmetric leg in the opposite step. The validation performed on a cohort of 20 subjects showed the viability of the approach.

Video surveillance has long been in use to monitor security sensitive areas such as banks, department stores, crowded public places and borders. The rise in computer speed, availability of cheap large-capacity storage devices and high speed network infrastructure enabled the way for cheaper, multi sensor video surveillance systems. In this thesis, the problem of tracking multiple targets with multiple cameras has been discussed. Cameras have been located so that they have overlapping fields of vision. A dynamic background-modeling algorithm is described for segmenting moving objects from the background, which is capable of adapting to dynamic scene changes and periodic motion, such as illumination change and swaying of trees. After segmentation of foreground scene, the objects to be tracked have been acquired by morphological operations and connected component analysis. For the purpose of tracking the moving objects, an active contour model (snakes) is one of the approaches, in addition to a Kalman tracker. As the main tracking algorithm, a rule based tracker has been developed first for a single camera, and then extended to multiple cameras. Results of used and proposed methods are given in detail.

Cette thèse s’intéresse à définir de nouvelles méthodes cliniques d’investigation permettant de juger de l’impact de l’avance en âge sur la motricité. En particulier, cette thèse se focalise sur deux principales perturbations possibles lors de l’avance en âge : la chute et l’altération de la marche.Ces deux perturbations motrices restent encore mal connues et leur analyse en clinique pose de véritables défis technologiques et scientifiques. Dans cette thèse, nous proposons des méthodes originales de détection qui peuvent être utilisées dans la vie courante ou en clinique, avec un minimum de contraintes techniques. Dans une première partie, nous abordons le problème de la détection de la chute à domicile, qui a été largement traité dans les années précédentes. En particulier, nous proposons une approche permettant d’exploiter le volume du sujet, reconstruit à partir de plusieurs caméras calibrées. Ces méthodes sont généralement très sensibles aux occultations qui interviennent inévitablement dans le domicile et nous proposons donc une approche originale beaucoup plus robuste à ces occultations. L’efficacité et le fonctionnement en temps réel ont été validés sur plus d’une vingtaine de vidéos de chutes et de leurres, avec des résultats approchant les 100% de sensibilité et de spécificité en utilisant 4 caméras ou plus. Dans une deuxième partie, nous allons un peu plus loin dans l’exploitation des volumes reconstruits d’une personne, lors d’une tâche motrice particulière : la marche sur tapis roulant, dans un cadre de diagnostic clinique. Dans cette partie, nous analysons plus particulièrement la qualité de la marche. Pour cela nous développons le concept d’utilisation de caméras de profondeur pour la quantification de l’asymétrie spatiale au cours du mouvement des membres inférieurs pendant la marche. Après avoir détecté chaque pas dans le temps, cette méthode réalise une comparaison de surfaces de chaque jambe avec sa correspondante symétrique du pas opposé. La validation effectuée sur une cohorte de 20 sujets montre la viabilité de la démarche. / This thesis is concerned with defining new clinical investigation method to assess the impact of ageing on motricity. In particular, this thesis focuses on two main possible disturbance during ageing : the fall and walk impairment. This two motricity disturbances still remain unclear and their clinical analysis presents real scientist and technological challenges. In this thesis, we propose novel measuring methods usable in everyday life or in the walking clinic, with a minimum of technical constraints. In the first part, we address the problem of fall detection at home, which was widely discussed in previous years. In particular, we propose an approach to exploit the subject’s volume, reconstructed from multiple calibrated cameras. These methods are generally very sensitive to occlusions that inevitably occur in the home and we therefore propose an original approach much more robust to these occultations. The efficiency and real-time operation has been validated on more than two dozen videos of falls and lures, with results approaching 100 % sensitivity and specificity with at least four or more cameras. In the second part, we go a little further in the exploitation of reconstructed volumes of a person at a particular motor task : the treadmill, in a clinical diagnostic. In this section we analyze more specifically the quality of walking. For this we develop the concept of using depth camera for the quantification of the spatial and temporal asymmetry of lower limb movement during walking. After detecting each step in time, this method makes a comparison of surfaces of each leg with its corresponding symmetric leg in the opposite step. The validation performed on a cohort of 20 subjects showed the viability of the approach. / Réalisé en cotutelle avec le laboratoire M2S de Rennes 2

No description available.