Thesis (Ph. D.)--Electrical and Computer Engineering, Georgia Institute of Technology, 2008. / Vela, Patricio, Committee Member ; Tannenbaum, Allen, Committee Member ; Yezzi, Anthony, Committee Chair ; Turk, Greg, Committee Member ; Lanterman, Aaron, Committee Member.

Thesis (M.Sc.)--York University, 2004. Graduate Programme in Computer Science. / Typescript. Includes bibliographical references (leaves 155-159). 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_val_fmt=info:ofi/fmt:kev:mtx:dissertation&rft_dat=xri:pqdiss:MR11828

Thesis (M.S.)--Naval Postgraduate School, 2006. / "December 2006." Includes bibliographical references (p. 47-48). Also available online from the Web site of the Naval Postgraduate School (http://www.nps.edu).

Thesis (Ph.D.)--York University, 2005. Graduate Programme in Computer Science. / Typescript. Includes bibliographical references (leaves 166-179). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://wwwlib.umi.com/cr/yorku/fullcit?pNR11643

This paper bridges the gap between variable selection methods (e.g., Pearson coefficients, KS test) and dimensionality reductionalgorithms (e.g., PCA, LDA). Variable selection algorithms encounter difficulties dealing with highly correlated data,since many features are similar in quality. Dimensionality reduction algorithms tend to combine all variables and cannotselect a subset of significant variables.Our approach combines both methodologies by applying variable selection followed by dimensionality reduction. Thiscombination makes sense only when using the same utility function in both stages, which we do. The resulting algorithmbenefits from complex features as variable selection algorithms do, and at the same time enjoys the benefits of dimensionalityreduction.1

In a mobile robotic system, the interaction with the surrounding environment is essential in order to complete tasks such as localisation and mapping. This interaction can only be conducted by means of sensors that permit the accumulation of a large amount of information from several sources. However, this information is useless without adequate interpretation; thus, in order to accurately determine the positioning of the robot, it is necessary to identify and characterise landmarks in the environment required to serve as anchoring points for both localisation and mapping. Having constructed the map, an accurate analysis of the information gathered is vital. In this manner, this work is focused on two main aspects of any mobile robotic system: first, the detection and characterisation of highly descriptive landmarks by using image and point cloud processing techniques; and second, the geometrical and spatial analysis of the information gathered from the environment. For the former, two novel techniques based on image processing and geometrical analysis are presented; for the latter, a guaranteed technique for the parameter estimation of primitive shapes using interval analysis is proposed.

The mapping problem is a major player in mobile robotics, and it is essential for many real applications such as disaster response or nuclear decommissioning. Generally, the robotic mapping is addressed under the umbrella of simultaneous localization and mapping (SLAM). Several probabilistic techniques were developed in the literature to approach the SLAM problem, and despite the good performance, their convergence proof is only limited to linear Gaussian models. This thesis proposes an interval SLAM (i-SLAM) algorithm as a new approach that addresses the robotic mapping problem in the context of interval methods. The noise of the robot sensor is assumed bounded, and without any prior knowledge of its distribution, we specify soft conditions that guarantee the convergence of robotic mapping for the case of nonlinear models with non-Gaussian noise. A new theory about compact sets is developed in the context of real analysis to conclude such conditions. Then, a case study is presented where the performance of i-SLAM is compared to the probabilistic counterparts in terms of accuracy and efficiency. Moreover, this work presents an application for i-SLAM using an RGB-D sensor that operates in unknown environments. Interval methods and computer vision techniques are employed to extract planar landmarks in the environment. Then, a new hybrid data association approach is developed using a modified version of bag-of-features method to uniquely identify different landmarks across timesteps. Finally, the results obtained using the proposed data association approach are compared to the typical least-squares approaches, thus demonstrating the consistency and accuracy of the proposed approach.

The objective of the research programme has been to investigate the behaviour of masonry arch vault collapse mechanisms in the context of the problems besetting the national bridge stock. The programme has primarily involved masonry constitutive theoretical studies, supported by laboratory experimentation, which have led to the formulation of novel masonry hinge modelling. The modelling has been developed for practical application in a four hinge masonry vault mechanism analysis and subjected to testing. The technique has been applied in the field supported by a novel application of information technology (IT) image processing, reflecting the growing importance of IT within the construction industry. All theoretical studies have been mounted as micro-computer software with graphics. The accent is upon engineering requirements in practice. Chapter One reviews the context and history of the masonry vault structural form, whose presence has long been commonplace in the United Kingdom, especially on the nation's road network. It is noted that elderly arched road bridges are under continual pressure to carry ever greater loads yet their strength is uncertain. Historically, structural analysts have attempted to resolve the arch's behaviour but present methods are still inexact. Chapter Two describes how, traditionally, masonry has been assumed to possess either a linear stress-strain property or infinite stiffness and strength. An alternative, novel equation for modelling masonry stress-strain laws is presented which may be configured to mimic the behaviour of real materials as well as that of the infinite strength and linear laws it replaces. A numerical analytical procedure has been developed to 'solve' rectangular masonry sections under combined bending and thrust thereby rendering the earlier approximations unnecessary. Chapter Three develops the theme further leading to the numerical determination of limit state hinge characteristics which furnish a static limit state axial thrust/bending moment interaction diagram and a corresponding serviceability limit state, prevention of cracking interaction diagram. Differentiation is thus made possible between hitherto identically-treated though varying natural materials and comparisons made. It is further postulated that any point on a static limit state interaction diagram locus represents a masonry hinge and an extensive series of laboratory model hinge tests is undertaken to demonstrate the point by testing the foregoing theoretical studies. Chapter Four describes the incorporation of the hinge theory into a mechanism-type computer analytical tool. Crucially, the analysis is different from other mechanism analyses by virtue of the hinge modelling, enabling the effects of material properties on arch behaviour to be studied. The software is tested in Chapter Five against prototype data for laboratory model and full size masonry bridges. Chapter Six introduces computer vision, an IT technique that is relatively novel to the structures field. It is adapted to monitor the above laboratory model arch tests and then extended to the monitoring of a multi-span arch bridge test in the field. Computer vision permits the formulation of a hypothesis regarding the unusual mode of failure that occurred and this is supported by a generalisation of the mechanism hinge theory, thereby demonstrating the merits of both techniques. Finally, Chapter Seven draws conclusions on the foregoing and makes suggestions for further work. Supporting documentation is given in the Appendices.

Developing an intelligent inspection system that can enhance the public safety is challenging. An efficient video analytics system can help monitor unusual events and mitigate possible damage or loss. This thesis aims to analyze surveillance video data, report abnormal activities and retrieve corresponding video clips. The surveillance video dataset used in this thesis is derived from ALERT Dataset, a collection of surveillance videos at airport security checkpoints. The video analytics system in this thesis can be thought as a pipelined process. The system takes the surveillance video as input, and passes it through a series of processing such as object detection, multi-object tracking, person-bin association and re-identification. In the end, we can obtain trajectories of passengers and baggage in the surveillance videos. Abnormal events like taking away other's belongings will be detected and trigger the alarm automatically. The system could also retrieve the corresponding video clips based on user-defined query.

De nos jours les méthodes de vision par ordinateur sont utilisées dans de nombreuses applications telles que la vidéo-surveillance, l'aide à la conduite ou la reconstruction 3D par exemple. Ces différentes applications s'appuient généralement sur des procédés de reconnaissance de formes ou de suivi. Pour ce faire, l'image est analysée afin d'en extraire des amers ou des primitives (contours, fonctions d'intensité ou modèles morphologiques). Les méthodes les plus courantes s'appuient sur l'utilisation de points d'intérêt représentant une discontinuité des niveaux de gris caractérisant un coin dans une image. Afin de mettre en correspondance un ensemble de points d'une image à une autre, une description locale est utilisée. Elle permet d'extraire l'information du voisinage de chaque point (valeurs des pixels, des intensités lumineuses, des gradients). Dans le cas d'applications telles que la vidéo-surveillance ou les caméras embarquées, l'ajout d'une information temporelle est fortement recommandé. Cette généralisation est utilisée au sein du laboratoire pour des projets de type véhicules intelligents (CyCab : véhicule intelligent, VELAC : VEhicule du Lasmea pour l'Aide à la Conduite). Les travaux de recherche présentés dans ce mémoire ont pour objectif de mettre en oeuvre différents outils de détection, description et mise en correspondance de points d'intérêt. Un certain nombre de contraintes a été établi, notamment l'utilisation d'images en niveaux de gris, la robustesse et l'aspect générique de la méthode. Dans un premier temps, nous proposons une analyse bibliographique des méthodes existantes. Cette dernière permet en effet d'en déduire les paramètres de mise en oeuvre ainsi que les principaux avantages et inconvénients. Nous détaillons par la suite la méthode proposée. La détection des primitives repose sur l'utilisation du détecteur fast-hessien que nous optimisons. L'utilisation d'une description locale basée sur des histogrammes de gradients orientés (HOG) est très répandue et procure de très bons résultats. Nous proposons de compléter son utilisation par un recalage et une mise à l'échelle d'un masque d'analyse elliptique créant ainsi une nouvelle forme de description locale (E-HOG). La mise en correspondance des points d'intérêt se base quant à elle sur une approche par corrélation à laquelle nous ajoutons un coefficient de sélection ainsi qu'une étape de suppression des doublons. Les différents résultats validant notre approche s'appuient sur l'utilisation de transformations synthétiques (vérité terrain) ou réelles. Nous proposons également une généralisation de notre approche au domaine spatiotemporel, permettant ainsi d'élargir son domaine d'utilisation. Le masque d'analyse précédemment cité est modifié et s'appuie donc sur l'utilisation d'ellipsoïdes. Les tests de validation reposent d'une part sur des séquences vidéo ayant subi des transformations synthétiques et d'autre part sur des séquences réelles issues de la plate-forme PAVIN (Plate-forme d'Auvergne pour Véhicules Intelligents). / Pas de résumé disponible