Thesis (Ph. D.)--Oregon State University, 2009. / Printout. Includes bibliographical references (leaves 103-109). Also available on the World Wide Web.

Zugl.: Aachen, Techn. Hochsch., Diss., 2007.

Zugl.: München, Techn. Univ., Diss., 2007

Zugl.: Duisburg, Essen, Univ., Diss., 2008

Thesis (Ph. D.)--University of Wisconsin, 1966. / Typescript. Vita. eContent provider-neutral record in process. Description based on print version record. Includes bibliographical references (leaves 94-96).

Zugl.: Clausthal, Techn. Univ., Diss., 2009

Thesis (Ph. D.)--University of Texas at Austin, 2005. / Supervisor: Diane Schallert. Vita. Includes bibliographical references.

Thesis (Ph.D.)--University of Delaware, 2006. / Principal faculty advisor: Guang R. Gao, Dept. of Electrical and Computer Engineering. Includes bibliographical references.

Thesis (M.S.)--Oregon State University, 2007. / Printout. Includes bibliographical references (leaves 36-37). Also available on the World Wide Web.

This thesis explores approaches to two problems in the frame-rate computation of a priori unknown 3D scene structure and camera pose using a single camera, or monocular simultaneous localisation and mapping. The thesis reflects two trends in vision in general and structure from motion in particular: (i) the move from directly recovered and towards learnt geometry; and (ii) the sparsification of otherwise dense direct methods. The first contributions mitigate scale drift. Beyond the inevitable accumulation of random error, monocular SLAM accumulates error via the depth/speed scaling ambiguity. Three solutions are investigated. The first detects objects of known class and size using fixed descriptors, and incorporates their measurements in the 3D map. Experiments using databases with ground truth show that metric accuracy can be restored over kilometre distances; and similar gains are made using a hand-held camera. Our second method avoids explicit feature choice, instead employing a deep convolutional neural network to yield depth priors. Relative depths are learnt well, but absolute depths less so, and recourse to database-wide scaling is investigated. The third approach uses a novel trained network to infer speed from imagery. The second part of the thesis develops sparsified direct methods for monocular SLAM. The first contribution is a novel camera tracker operating directly using affine image warping, but on patches around sparse corners. Camera pose is recovered with an accuracy at least equal to the state of the art, while requiring only half the computational time. The second introduces a least squares adjustment to sparsified direct map refinement, again using patches from sparse corners. The accuracy of its 3D structure estimation is compared with that from the widely used method of depth filtering. It is found empirically that the new method's accuracy is often higher than that of its filtering counterpart, but that the method is more troubled by occlusion.