This thesis introduces novel algorithms for 3D shape recovery under multiple viewpoints and single viewpoint. Surface of a 3D object is reconstructed by either graph-cuts using images under multiple viewpoints, depth from reflection under a fixed viewpoint, or depth from refraction under a fixed viewpoint. The first part of this thesis revisits the graph-cuts based approach for solving the multi-view stereo problem and proposes a novel foreground / background energy. Unlike traditional graph-cuts based methods which focus on the photo-consistency energy, this thesis targets at deriving a robust and unbiased foreground / background energy which depends on data. It is shown that by using the proposed foreground / background energy, it is possible to recover the object surface from noisy depth maps even in the absence of the photo-consistency energy, which demonstrates the effectiveness of the proposed energy. In the second part of this thesis, a novel method for shape recovery is proposed based on reflection of light using a spherical mirror. Unlike other existing methods which require the prior knowledge of the position and the radius of the spherical mirror, it is shown in this thesis that the object can be reconstructed up to an unknown scale using an unknown spherical mirror. This thesis finally considers recovering object surfaces based on refraction of light and presents a novel depth from refraction method. A scene is captured several times by a fixed camera, with the first image (referred to as the direct image) captured directly by the camera and the others (referred to as the refracted images) by placing a transparent medium with two parallel planar faces between the scene and the camera. With a known pose and refractive index of the medium, a depth map of the scene is then recovered from the displacements of scene points in the images. Unlike traditional depth from refraction methods which require extra steps to estimate the pose and the refractive index of the medium, this thesis presents a novel method to estimate them from the direct and refracted images of the scene. It is shown that the pose of the medium can be recovered from one direct image and one refracted image. It is also shown that the refractive index of the medium can be recovered with a third image captured with the medium placed in a different pose. / published_or_final_version / Computer Science / Doctoral / Doctor of Philosophy

Many computer vision problems involve building automatic systems by extracting complex high-level information from visual data. Such problems can often be modeled using structural models, which relate raw input variables to structural high-level output variables. Structural support vector machine is a discriminative method for learning structural models. It allows a flexible feature construction with good robustness against overfitting, and thus provides state-of-the-art prediction accuracies for structural prediction tasks in computer vision. This thesis first studies the application of structural SVMs in interactive image segmentation. A novel interactive image segmentation technique that automatically learns segmentation parameters tailored for each and every image is proposed. Unlike existing work, the proposed method does not require any offline parameter tuning or training stage, and is capable of determining image-specific parameters according to some simple user interactions with the target image. The segmentation problem is modeled as an inference of a conditional random field (CRF) over a segmentation mask and the target image. This CRF is parametrized by the weights for different terms (e.g., color, texture and smoothing). These weight parameters are learned via a one-slack structural SVM, which is solved using a constraint approximation scheme and the cutting plane algorithm. Experimental results show that the proposed method, by learning image-specific parameters automatically, outperforms other state-of-the-art interactive image segmentation techniques. This thesis then uses structural SVMs to speed up large scale relatively-paired space analysis. A new multi-modality analysis technique based on relatively-paired observations from multiple modalities is proposed. Relative-pairing information is encoded using relative proximities of observations in a latent common space. By building a discriminative model and maximizing a distance margin, a projection function that maps observations into the latent common space is learned for each modality. However, training based on large scale relatively-paired observations could be extremely time consuming. To this end, the training is reformulated as learning a structural model, which can be optimized by the cutting plane algorithm where only a few training samples are involved in each iteration. Experimental results validate the effectiveness and efficiency of the proposed technique. / published_or_final_version / Computer Science / Doctoral / Doctor of Philosophy

This paper discusses the design of an autonomous remote-controlled racecar to play a one-on-one match of capture the flag. A competition was held, and the results are presented and conclusions are made.

MEMS technology is a growing field that requires more automative tools to lower the cost of production. Current industry standards of tele-operated 3D manipulated MEMS parts to create new devices are labor intensive and expensive process. Using computer vision as a main feedback tool to recognize parts on chip, it is possible to program a close loop system to instruct a computer to pick and assemble parts on the chip without the aid of a user. To make this process a viable means, new chip designs, robotic systems and computer vision algorithms working along side with motion controllers have to be developed. / Graduate / 0548 / 0544 / 0771 / hsukardi@uvic.ca

No description available.

No description available.

There are many different algorithms that have been shown to solve the simultaneous localization and mapping (SLAM) problem depending on the type of input data. Many of these algorithms use some form of cumulative current position as a state variable and only store landmarks in their globally mapped form, discarding past data. This thesis takes a different approach in not using current position as a cumulative state variable and storing and using past data. Landmarks are mapped relative to each other in their untransformed states and use either three points or one plane to maintain translation and rotation invariance. The Relative algorithms can use both current and past data for accuracy purposes. Using this approach, the SLAM problem is solved by data structures and algorithms rather than probabilistic modeling. The Relative algorithms are shown to be good solutions to the simulated SLAM problems tested in this thesis. In particular the Relative Point algorithm is shown to have a worst case computation complexity of O(nslogns). ns is the average quantity of points observed in a given observation and is not related to the total quantity of points on the map. The Relative Point algorithm is able to identify points with movement that is not correlated to the viewpoint at a low cost, and has comparable accuracy to a 6D no odometry Extended Kalman Filter.

No description available.

No description available.

No description available.