The recent growth in inexpensive laser scanning sensors has created entire fields of research aimed at processing this data. One application is determining the polygonal boundaries of roofs, as seen from an overhead view. The resulting building outlines have many commercial as well as military applications. My work in this area has created a segmentation algorithm where the descriptive features are computationally and theoretically simpler than previous methods. A support vector machine is used to segment data points using these features, and their use is not common for roof detection to date. Despite the simplicity of the feature calculations, the accuracy of our algorithm is similar to previous work. I also describe a basic polygonal extraction method, which is acceptable for basic roofs.

The rising statistics of fatal and non-fatal injuries involving an all-terrain vehicle has called for an analysis of the accumulated data from the past years. The analysis has led to the conclusion that in the past years, the fatal and non-fatal injuries have been rising rapidly in spite of the consent decrees which were brought into effect from 1988-1998 by the consumer product safety commission. A necessity to provide increased safety while riding an all-terrain vehicle is recognized. Rollover protective structures which were used with successful results in curbing the injuries on agricultural tractors have been identified as having a potential to serve the purpose. A conceptual design of an automatically deployable rollover protective structure has been dealt with, in the thesis.

Les glissements de terrain sont à l'origine de la destruction de nombreuses infrastructures routières, de bâtiments et causent la perte de vies humaines. L'observation des glissements de terrain est limitée par l'absence d'archives historiques précises. Sur les glissements de terrain superficiels forestiers, la dendrogéomorphologie permet de reconstruire, avec une résolution temporelle saisonnière et une emprise spatiale décamétrique, l'activité du processus, à partir de l'analyse des perturbations anatomiques contenues dans les cernes de croissance. 13 glissements de terrain superficiels forestiers, localisés dans la vallée de l'Ubaye ont été étudiés. L'analyse dendrogéomorphologique permet de densifier les chroniques historiques, d'obtenir des périodes de retour et d'améliorer nos connaissances sur le comportement spatial du processus. L'approche statistique basée sur un modèle de Poisson, permet de quantifier et de cartographier des probabilités de réactivation. La thèse proposera d'évaluer la robustesse de la reconstruction dendrogéomorphologique ainsi que le rôle des précipitations dans le déclenchement des évènements passé.

A descent into the ravine is a step through a tear in urbanity. The terrain vague is a foil to the capitalist city; against a demand for order, specificity, and integration, it is disorienting, banal, erratic. Operating outside the constraints of dominant social structures, it harbours the unconscious of the city, not only an inevitable, but also a necessary rupture in the urban fabric. In this subterranean realm, the striated and measured plots of land are sporadically smoothed over by persistent nature, reclaiming its territory. These perceived voids invite projections of desire, both at a civic scale and on an individual level, that consequently shape the space. These are grounds of negotiation, a political realm often driven more by visceral impulses than economics. They aggravate tensions typically suppressed in the city, including those wrought by violence and melancholy. This is a portrait of the Don Valley in Toronto. Fragments of representation reveal the role of this space in the collective memory of the public. Beyond the infrastructure that binds them, the city and the valley are integrated through their opposition: one fuels the experience of the other.

The ability of robotic units to navigate various terrains is critical to the advancement of robotic operation in real world environments. Next generation robots will need to adapt to their environment in order to accomplish tasks that are either too hazardous, too time consuming, or physically impossible for human-beings. Such tasks may include accurate and rapid explorations of various planets or potentially dangerous areas on planet Earth. This research investigates a navigation control methodology for a wheel-legged robot based on active vision. The method presented is designed to control the reconfigurability of the robot (i.e. control the usage of the wheels and legs), depending upon the obstacle/terrain, based on perception. Surface estimation for robot reconfigurability is implemented using a region growing method and a characterization and traversability assessment generated from camera data. As a result, a mathematical approach that directs necessary navigation behavior is implemented to control robot mobility. The hybrid wheeled-legged rover possesses a four-legged or six-legged walking system as well as a four-wheeled mobility system.

Thesis (M.A. Sc.)--University of Toronto, 2004. / Adviser: G.M.T. D'Eleuterio.

Mémoire (M.Ed.)--Université du Québec à Chicoutimi, 1997. / Document électronique également accessible en format PDF. CaQCU

Thesis (M.App.Sc.) - Carleton University, 2007. / Includes bibliographical references (p. 108-112). Also available in electronic format on the Internet.

In this thesis, we design and develop new approximation algorithms and complexity results for three guarding and partitioning problems on orthogonal polygons; namely, guarding orthogonal polygons using sliding cameras, partitioning orthogonal polygons so as to minimize the stabbing number and guarding orthogonal terrains using vertex guards. We first study a variant of the well-known art gallery problem in which sliding cameras are used to guard the polygon. We consider two versions of this problem: the Minimum- Cardinality Sliding Cameras (MCSC) problem in which we want to guard P with the minimum number of sliding cameras, and the Minimum-Length Sliding Cameras (MLSC) problem in which the goal is to compute a set S of sliding cameras for guarding P so as to minimize the total length of trajectories along which the cameras in S travel. We answer questions posed by Katz and Morgenstern (2011) by presenting the following results: (i) the MLSC problem is polynomially tractable even for orthogonal polygons with holes, (ii) the MCSC problem is NP-complete when P is allowed to have holes, and (iii) an O(n)-time exact algorithm for the MCSC problem on monotone polygons. We then study a conforming variant of the problem of computing a partition of an orthogonal polygon P into rectangles whose stabbing number is minimum over all such partitions of P. The stabbing number of such a partition is the maximum number of rectangles intersected by any orthogonal line segment inside the polygon. In this thesis, we first give an O(n log n)-time algorithm that solves this problem exactly on histograms. We then show that the problem is NP-hard for orthogonal polygons with holes, providing the first hardness result for this problem. To complement the NP-hardness result, we give a 2-approximation algorithm for the problem on both polygons with and without holes. Finally, we study a variant of the terrain guarding problem on orthogonal terrains in which the objective is to guard the vertices of an orthogonal terrain with the minimum number of vertex guards. We give a linear-time algorithm for this problem under a directed visibility constraint. / February 2016

abstract: Advancements in computer vision and machine learning have added a new dimension to remote sensing applications with the aid of imagery analysis techniques. Applications such as autonomous navigation and terrain classification which make use of image classification techniques are challenging problems and research is still being carried out to find better solutions. In this thesis, a novel method is proposed which uses image registration techniques to provide better image classification. This method reduces the error rate of classification by performing image registration of the images with the previously obtained images before performing classification. The motivation behind this is the fact that images that are obtained in the same region which need to be classified will not differ significantly in characteristics. Hence, registration will provide an image that matches closer to the previously obtained image, thus providing better classification. To illustrate that the proposed method works, naïve Bayes and iterative closest point (ICP) algorithms are used for the image classification and registration stages respectively. This implementation was tested extensively in simulation using synthetic images and using a real life data set called the Defense Advanced Research Project Agency (DARPA) Learning Applied to Ground Robots (LAGR) dataset. The results show that the ICP algorithm does help in better classification with Naïve Bayes by reducing the error rate by an average of about 10% in the synthetic data and by about 7% on the actual datasets used. / Dissertation/Thesis / M.S. Electrical Engineering 2011