We propose three biometric systems for performing 1) Multi-modal Three-Dimensional (3D) ear + Two-Dimensional (2D) face recognition, 2) 3D face recognition, and 3) hybrid 3D ear recognition combining local and holistic features. For the 3D ear component of the multi-modal system, uncalibrated video sequences are utilized to recover the 3D ear structure of each subject within a database. For a given subject, a series of frames is extracted from a video sequence and the Region-of-Interest (ROI) in each frame is independently reconstructed in 3D using Shape from Shading (SFS). A fidelity measure is then employed to determine the model that most accurately represents the 3D structure of the subject’s ear. Shape matching between a probe and gallery ear model is performed using the Iterative Closest Point (ICP) algorithm. For the 2D face component, a set of facial landmarks is extracted from frontal facial images using the Active Shape Model (ASM) technique. Then, the responses of the facial images to a series of Gabor filters at the locations of the facial landmarks are calculated. The Gabor features are stored in the database as the face model for recognition. Match-score level fusion is employed to combine the match scores obtained from both the ear and face modalities. The aim of the proposed system is to demonstrate the superior performance that can be achieved by combining the 3D ear and 2D face modalities over either modality employed independently. For the 3D face recognition system, we employ an Adaboost algorithm to builda classifier based on geodesic distance features. Firstly, a generic face model is finely conformed to each face model contained within a 3D face dataset. Secondly, the geodesic distance between anatomical point pairs are computed across each conformed generic model using the Fast Marching Method. The Adaboost algorithm then generates a strong classifier based on a collection of geodesic distances that are most discriminative for face recognition. The identification and verification performances of three Adaboost algorithms, namely, the original Adaboost algorithm proposed by Freund and Schapire, and two variants – the Gentle and Modest Adaboost algorithms – are compared. For the hybrid 3D ear recognition system, we propose a method to combine local and holistic ear surface features in a computationally efficient manner. The system is comprised of four primary components, namely, 1) ear image segmentation, 2) local feature extraction and matching, 3) holistic feature extraction and matching, and 4) a fusion framework combining local and holistic features at the match score level. For the segmentation component, we employ our method proposed in [111], to localize a rectangular region containing the ear. For the local feature extraction and representation component, we extend the Histogram of Categorized Shapes (HCS) feature descriptor, proposed in [111], to an object-centered 3D shape descriptor, termed Surface Patch Histogram of Indexed Shapes (SPHIS), for surface patch representation and matching. For the holistic matching component, we introduce a voxelization scheme for holistic ear representation from which an efficient, element-wise comparison of gallery-probe model pairs can be made. The match scores obtained from both the local and holistic matching components are fused to generate the final match scores. Experimental results conducted on the University of Notre Dame (UND) collection J2 dataset demonstrate that theproposed approach outperforms state-of-the-art 3D ear biometric systems in both accuracy and efficiency.

The study proposes an application of Talens (2003) methodological framework for assessing neighbourhood-level (i.e., non-motorised mode) accessibility, and offers recommendations for improving non-motorized transportation (NMT) accessibility to enhance multimodal integration between bicycles and buses in contemporary North American suburban neighbourhoods. Accessibility (or access) is defined as the average travel time or distance between a given origin and destination along the shortest available street network route. The study considers characteristics of the transportation network such as available route directness, facilities, and transit service provision to determine their impacts on bicycle access. A further methodology for comparing bicycle versus bus modal efficiencies within suburban contexts is developed and applied to the case study. A review of approaches designed to promote bicycling while discouraging personal automobile use provides a toolbox of proven treatments that are applied to a case study of Saskatoon, Saskatchewan a city of approximately 200,000 people. The approach provides a process that can be used by city or transit planners to identify neighbourhoods that lack sufficient access and apply treatments that improve bicycle accessibility and bicycle-transit integration. Results suggest existing potential for the bicycle as an access mode within contemporary suburban neighbourhood transportation networks. The case study supports the notion that suburban bicycle-bus integration could be used as a viable alternative to automobiles for daily home-to-node activity trips, and raises questions about the current allocation of public transit service to suburban routes within the context of the case study. Discussion and conclusions suggest directions for future research in this field of sustainable urban transportation planning.

According to the United Nations’ report, State of World Population 2008, humankind has come to a turning point; more than 50% of the earth’s population now lives in urban centres. Along with considerations for housing, employment, and public health, this shift changes the way we design roads and streets; it escalates the number of automobiles in urban areas with finite room for road expansion. Space constraints, along with intense development of alternative transportation fuels, and the burden of sprawling suburbs on municipal infrastructures suggest the hypothesis that before we run out of energy alternatives for personal mechanized transport, we will run out of space in which to use it. This thesis explores how Toronto, a city largely designed for automobile use, is being re-adapted into a city wherein public and active transportation can once again be the primary means of urban mobility and the opportunities inherent in the development of interregional multi-modal transit stations for the cultivation of civic space, local commerce, urban form, and commercial transportation.

The study proposes an application of Talens (2003) methodological framework for assessing neighbourhood-level (i.e., non-motorised mode) accessibility, and offers recommendations for improving non-motorized transportation (NMT) accessibility to enhance multimodal integration between bicycles and buses in contemporary North American suburban neighbourhoods. Accessibility (or access) is defined as the average travel time or distance between a given origin and destination along the shortest available street network route. The study considers characteristics of the transportation network such as available route directness, facilities, and transit service provision to determine their impacts on bicycle access. A further methodology for comparing bicycle versus bus modal efficiencies within suburban contexts is developed and applied to the case study. A review of approaches designed to promote bicycling while discouraging personal automobile use provides a toolbox of proven treatments that are applied to a case study of Saskatoon, Saskatchewan a city of approximately 200,000 people. The approach provides a process that can be used by city or transit planners to identify neighbourhoods that lack sufficient access and apply treatments that improve bicycle accessibility and bicycle-transit integration. Results suggest existing potential for the bicycle as an access mode within contemporary suburban neighbourhood transportation networks. The case study supports the notion that suburban bicycle-bus integration could be used as a viable alternative to automobiles for daily home-to-node activity trips, and raises questions about the current allocation of public transit service to suburban routes within the context of the case study. Discussion and conclusions suggest directions for future research in this field of sustainable urban transportation planning.

According to the United Nations’ report, State of World Population 2008, humankind has come to a turning point; more than 50% of the earth’s population now lives in urban centres. Along with considerations for housing, employment, and public health, this shift changes the way we design roads and streets; it escalates the number of automobiles in urban areas with finite room for road expansion. Space constraints, along with intense development of alternative transportation fuels, and the burden of sprawling suburbs on municipal infrastructures suggest the hypothesis that before we run out of energy alternatives for personal mechanized transport, we will run out of space in which to use it. This thesis explores how Toronto, a city largely designed for automobile use, is being re-adapted into a city wherein public and active transportation can once again be the primary means of urban mobility and the opportunities inherent in the development of interregional multi-modal transit stations for the cultivation of civic space, local commerce, urban form, and commercial transportation.

No description available.

Résumé : Le recalage automatique des images issues de la tomographie par émission de positrons (TEP) et de l’imagerie par résonance magnétique (IRM) du petit animal pose un problème difficile à résoudre, tant sur l’aspect de la précision, du taux de réussite et de convergence que sur la rapidité d’exécution. En fait, la plupart des techniques de recalage actuelles sont développées et appliquées aux cerveaux humains, mais ne sont pas aussi efficaces lorsqu’appliquées sur des données animales. L’anisotropie impor¬tante des voxels (résolution fine dans le plan de l’acquisition, mais grande épaisseur de coupe) et la dégradation des images associée à ce type d’acquisition s’additionne au manque d’information d’intensité et de complexité anatomique de ce type de jeu de données. Ce mémoire met l’accent sur les techniques multimodales de recalage automatique et de leurs limites, appliquées particulièrement à la TEP et l’IRM du petit animal. Dans l’article principal présenté dans ce mémoire, nous proposons une mesure qui utilise un recalage multirésolution en parallèle (imbriqué dans la fonction d’énergie) au lieu d’une approche classique de multirésolution séquentielle, influen¬çant directement la procédure du recalage. En combinant les niveaux de basse et haute résolution des images, nous nous assurons une plus grande insensibilité par rapport au bruit, d’une ouverture accrue permettant une meilleure convergence et rapidité d’exécution. L’article démontre que notre nouvelle approche automatique est un algorithme de recalage robuste et efficace avec un taux de réussite élevé. Nous présentons également dans ce mémoire certains détails d’implantation de l’outil, qui a été créé par l’auteur de ce document, reposant sur le recalage classique et la nouvelle méthode décrite dans ce mémoire.||Abstract: Automatic registration of small animal Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) data represents a difficult problem in terms of convergence speed, accuracy and success rate. In fact, most existing registration methods are developed and applied to human brain volumes but these are not as effective for small animal data because of the lack of intensity information in the images and often the large anisotropy in voxel dimensions (very small in-plane resolution and large slice thickness). This master thesis focuses on multi-modal automatic registration techniques and their limitations, especially applied to PET-MRI registration. In the main article of this master thesis, we propose a new registration measure that combines multi-resolution in parallel (in the same energy function) instead of a classic sequential multi-resolution, which influence the procedure of the registration as well. By combining low and high resolution levels of images, we can gain from the low noise sensitivity and aperture at coarse levels and higher contrast and details at higher levels, which helps convergence accuracy and speed. The paper shows that our new approach is therefore an automatic, robust and efficient registration algorithm with a high success rate. We also present in this document some implementation details on the tool which was created by the author of this thesis based on the classic registration and the new approach described in this thesis.

Category-level object recognition is a fundamental capability for the potential use of robots in the assistance of humans in useful tasks. There have been numerous vision-based object recognition systems yielding fast and accurate results in constrained environments. However, by depending on visual cues, these techniques are susceptible to object variations in size, lighting, rotation, and pose, all of which cannot be avoided in real video data. Thus, the task of object recognition still remains very challenging. My thesis work builds upon the fact that robots can observe humans interacting with the objects in their environment. We refer to the set of objects, which can be involved in the interaction as `interactionable' objects. The interaction of humans with the `interactionable' objects provides numerous nonvisual cues to the identity of objects. In this thesis, I will introduce a flexible object recognition approach called Multiple-Cue Object Recognition (MCOR) that can use multiple cues of any predefined type, whether they are cues intrinsic to the object or provided by observation of a human. In pursuit of this goal, the thesis will provide several contributions: A representation for the multiple cues including an object definition that allows for the flexible addition of these cues; Weights that reflect the various strength of association between a particular cue and a particular object using a probabilistic relational model, as well as object displacement values for localizing the information in an image; Tools for defining visual features, segmentation, tracking, and the values for the non-visual cues; Lastly, an object recognition algorithm for the incremental discrimination of potential object categories. We evaluate these contributions through a number of methods including simulation to demonstrate the learning of weights and recognition based on an analytical model, an analytical model that demonstrates the robustness of the MCOR framework, and recognition results on real video data using a number of datasets including video taken from a humanoid robot (Sony QRIO), video captured from a meeting setting, scripted scenarios from outside universities, and unscripted TV cooking data. Using the datasets, we demonstrate the basic features of the MCOR algorithm including its ability to use multiple cues of different types. We demonstrate the applicability of MCOR to an outside dataset. We show that MCOR has better recognition results over vision-only recognition systems, and show that performance only improves with the addition of more cue types.

In this paper we describe a technique of classifier combination used in a human identification system. The system integrates all available features from multi-modal sources within a Bayesian framework. The framework allows representinga class of popular classifier combination rules and methods within a single formalism. It relies on a “per-class” measure of confidence derived from performance of each classifier on training data that is shown to improve performance on a synthetic data set. The method is especially relevant in autonomous surveillance setting where varying time scales and missing features are a common occurrence. We show an application of this technique to the real-world surveillance database of video and audio recordings of people collected over several weeks in the office setting.

abstract: The purpose of this study was to investigate the effect of partial exemplar experience on category formation and use. Participants had either complete or limited access to the three dimensions that defined categories by dimensions within different modalities. The concept of "crucial dimension" was introduced and the role it plays in category definition was explained. It was hypothesized that the effects of partial experience are not explained by a shifting of attention between dimensions (Taylor & Ross, 2009) but rather by an increased reliance on prototypical values used to fill in missing information during incomplete experiences. Results indicated that participants (1) do not fill in missing information with prototypical values, (2) integrate information less efficiently between different modalities than within a single modality, and (3) have difficulty learning only when partial experience prevents access to diagnostic information. / Dissertation/Thesis / M.S. Psychology 2011