Robust image matching for object surface reconstruction
Abstract
The Constrained Optimal Surface Tracking (COST) algorithm is developed for object surface reconstruction. The matching problems are addressed by the integration of signal and feature matching. The innovative strategy arises within the framework of global optimization of the match function by dynamic programming. To increase computing speed, the algorithm is designed in such a way that it can be implemented in either a parallel or a sequential computing system. A conventional feature matching method based on dynamic programming is investigated and improved in this research. Many types of primitive features are extracted from the images, along with their position in epipolar space. These features include a straight line feature, plateau feature, edge feature, and spike point feature. Once the matched pairs are determined, object coordinates of feature points can be obtained. The signal matching process is driven from the object space. The concept of dynamic programming for line following is applied to determine the optimal elevation profile between two endpoints of a grid line. During the optimization process, the object coordinates from the results of feature matching are used as constraints. Once the optimal profiles from all gridlines are obtained, the object surface model can be reconstructed. To evaluate the performance of the algorithm, images of both urban and rural scenes have been tested. The experiments have shown promising results using this approach.
Degree
Ph.D.
Advisors
Bethel, Purdue University.
Subject Area
Civil engineering
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.