This thesis presents there important results in visual object recognition based on shape. (1) A new algorithm (RAST; Recognition by Adaptive Sudivisions of Tranformation space) is presented that has lower average-case complexity than any known recognition algorithm. (2) It is shown, both theoretically and empirically, that representing 3D objects as collections of 2D views (the "View-Based Approximation") is feasible and affects the reliability of 3D recognition systems no more than other commonly made approximations. (3) The problem of recognition in cluttered scenes is considered from a Bayesian perspective; the commonly-used "bounded-error errorsmeasure" is demonstrated to correspond to an independence assumption. It is shown that by modeling the statistical properties of real-scenes better, objects can be recognized more reliably.

Thesis (Ph.D.)--University of Delaware, 2006. / Principal faculty advisor: Chandra Kambhamettu, Dept. of Computer & Information Sciences. Includes bibliographical references.

Thesis (M.Sc.)--York University, 2003. Graduate Programme in Computer Science. / Typescript. Includes bibliographical references (leaves 104-111). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://gateway.proquest.com/openurl?url%5Fver=Z39.88-2004&res%5Fdat=xri:pqdiss&rft%5Fval%5Ffmt=info:ofi/fmt:kev:mtx:dissertation&rft%5Fdat=xri:pqdiss:MQ99410

Ce manuscrit de thèse a pour sujet la ré-identification de personne basée sur leur apparence à partir d'images et de vidéos. La ré-identification de personne consiste à déterminer si un individu donné est déjà apparu sur un réseau de caméras. Ce problème est particulièrement difficile car l'apparence change significativement entre les différentes vues de caméra, où les variations de points de vue, d'illumination et de position de l'objet, rendent le problème difficile. Nous nous concentrons sur le développement de modèles d'apparence robustes qui sont en mesure de faire correspondre les apparences humaines enregistrées dans des vues de caméra disjointes. Comme la représentation de régions d'image est fondamentale pour la mise en correspondance d'apparence, nous étudions différents types de descripteurs d'images. Ces différents descripteurs impliquent des stratégies différentes pour la mise en correspondance d'apparence, impliquant des modèles différents pour la représentation des apparences de personne. En appliquant des techniques d'apprentissage automatique, nous générons des modèles descriptifs et discriminatoires, qui améliorent la distinction des caractéristiques extraites, améliorant ainsi la précision de la ré-identification. Cette thèse a les contributions suivantes. Nous proposons six techniques de ré-identification humaine. Les deux premières appartiennent aux approches single-shot, dans lesquelles une seule image est suffisante pour extraire une signature fiable de personne. Ces approches divisent le corps humain en différentes parties de corps prédéfinies, puis extraient les caractéristiques de l'image. Cela permet de mettre en correspondance les différentes parties du corps en comparant les signatures. Les quatre autres méthodes abordent le problème de ré-identification à l'aide de signatures calculées à partir de plusieurs images (multiple-shot). Nous proposons deux techniques qui apprennent en ligne le modèle d'apparence humaine en utilisant un schéma de boosting. Les approches de boosting améliorent la précision de la reconnaissance, au détriment du temps de calcul. Les deux dernières approches assument un modèle prédéfini, ou un apprentissage hors ligne des modèles, pour réduire le temps de calcul. Nous constatons que le descripteur de covariance est en général le meilleur descripteur pour la mise en correspondance des apparences dans des vues de caméras disjointes. Comme l'opérateur de distance de ce descripteur nécessite un calcul intensif, nous proposons également une nouvelle implémentation utilisant le GPU qui accélère considérablement les temps de calcul. Nos expériences suggèrent que la moyenne Riemannienne des covariances calculée à partir de plusieurs images améliore les performances par rapport aux techniques de ré-identification de personne de l'état de l'art. Enfin, nous proposons deux nouvelles bases d'images d'individus pour évaluer le scénario multiple-shot.

No description available.

Tracking of an object's full six degree-of-freedom (6-dof) position and orientation (pose) would allow a robotic system to autonomously perform a variety of complex tasks, such as docking from any preferred angle, surveillance of moving subjects, etc. Computer vision has been commonly advocated as an effective tool for 3D (i.e., 6-dof) tracking Objects of Interest (OIs). However, the vast majority of vision-based 6-dof pose trackers reported in the literature require a model of the OI to be provided a priori. Finding/selecting the OI to track is also essential to autonomous operation. A problem that has often been neglected. This Thesis proposes a novel, real-time object-tracking system that solves all of the aforementioned problems. The tracking procedure begins with OI selection. Since what constitutes an OI is application dependent, selection is achieved via a customizable framework of Interest Filters (IFs) that highlight regions of interest within an image. The region of greatest interest becomes the selected OI. Next, an approximate visual 3D model of the selected OI is built on-line by a real-time modeller. Unlike previously proposed techniques, this modeller can build the model of the OI even in the presence of background clutter; an essential task for tracking one object amongst many. Once a model is built, a real-time 6-dof tracker (i.e., the third sub-component) performs the actual 6-dof object tracking via 3D model projection and optical flow. Performing simultaneous modelling and tracking presents several challenges requiring novel solutions. For example, a novel data-reduction scheme based on colour-gradient redundancy is proposed herein that facilitates using colour input images whilst still maintaining real-time performance on current computer hardware. Likewise, a per-pixel occlusion-rejection scheme is proposed which enables tracking in the presence of partial occlusions. Various other techniques have also been developed within the framework of this Thesis in order to achieve real-time efficiency, robustness to lighting variations, ability to cope with high OI speeds, etc. Extensive experiments with both synthetic and real-world motion sequences have demonstrated the ability of the proposed object-tracking system to track a priori unknown objects. The proposed algorithm has also been tested within two target applications: autonomous convoying, and dynamic camera reconfiguration.

In certain industries, quality testing is crucial, to make sure that the components being manufactured do not contain any defects. One method to detect these defects is to heat the specimen being inspected and then to study the cooling process using infrared thermography. The explorations of non-destructive testing using thermography is at an early stage and therefore the purpose of this thesis is to analyse some of the existing techniques and to propose improvements. A test specimen containing several different defects was designed specifically for this thesis. A flash lamp was used to heat the specimen and a high-speed infrared camera was used to study both the spatial and temporal features of the cooling process. An algorithm was implemented to detect anomalies and different parameter settings were evaluated. The results show that the proposed method is successful at finding the searched for defects, and also outperforms one of the old methods.

University of Macau / Faculty of Science and Technology / Department of Computer and Information Science

Tracking of an object's full six degree-of-freedom (6-dof) position and orientation (pose) would allow a robotic system to autonomously perform a variety of complex tasks, such as docking from any preferred angle, surveillance of moving subjects, etc. Computer vision has been commonly advocated as an effective tool for 3D (i.e., 6-dof) tracking Objects of Interest (OIs). However, the vast majority of vision-based 6-dof pose trackers reported in the literature require a model of the OI to be provided a priori. Finding/selecting the OI to track is also essential to autonomous operation. A problem that has often been neglected. This Thesis proposes a novel, real-time object-tracking system that solves all of the aforementioned problems. The tracking procedure begins with OI selection. Since what constitutes an OI is application dependent, selection is achieved via a customizable framework of Interest Filters (IFs) that highlight regions of interest within an image. The region of greatest interest becomes the selected OI. Next, an approximate visual 3D model of the selected OI is built on-line by a real-time modeller. Unlike previously proposed techniques, this modeller can build the model of the OI even in the presence of background clutter; an essential task for tracking one object amongst many. Once a model is built, a real-time 6-dof tracker (i.e., the third sub-component) performs the actual 6-dof object tracking via 3D model projection and optical flow. Performing simultaneous modelling and tracking presents several challenges requiring novel solutions. For example, a novel data-reduction scheme based on colour-gradient redundancy is proposed herein that facilitates using colour input images whilst still maintaining real-time performance on current computer hardware. Likewise, a per-pixel occlusion-rejection scheme is proposed which enables tracking in the presence of partial occlusions. Various other techniques have also been developed within the framework of this Thesis in order to achieve real-time efficiency, robustness to lighting variations, ability to cope with high OI speeds, etc. Extensive experiments with both synthetic and real-world motion sequences have demonstrated the ability of the proposed object-tracking system to track a priori unknown objects. The proposed algorithm has also been tested within two target applications: autonomous convoying, and dynamic camera reconfiguration.

We are addressing two aspects of vision based system development that are not fully exploited in current frameworks: abstraction over low-level details and high-level module reusability. Through an evaluation of existing frameworks, we relate these shortcomings to the lack of systematic classification of sub-tasks in vision based system development. Our approach for addressing these two issues is to classify vision into decoupled sub-tasks, hence defining a clear scope for a vision based system development framework and its sub-components. Firstly, we decompose the task of vision system development into data management and processing. We then proceed to further decompose data management into three components: data access, conversion and transportation. To verify our approach for vision system development we present two frameworks: the Vision Utility (VU) framework for providing abstraction over the data management component; and the Hive framework for providing the data transportation and high-level code reuse. VU provides the data management functionality for developers while hiding the low-level system details through a simple yet flexible Application Programming Interface (API). VU mediates the communication between the developer's application, vision processing modules, and data sources by utilizing different frameworks for data access, conversion and transportation (Hive). We demonstrate VU's ability for providing abstraction over low-level system details through the examination of a vision system developed using the framework. Hive is a standalone event based framework for developing distributed vision based systems. Hive provides simple high-level methods for managing communication, control and configuration of reusable components. We verify the requirements of Hive (reusability and abstraction over inter-module data transportation) by presenting a number of different systems developed on the framework using a set of reusable modules. Through this work we aim to demonstrate that this novel approach for vision system development could fundamentally change vision based system development by addressing the necessary abstraction, and promoting high-level code reuse.