Date of Award
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Dense matching and image segmentation are fundamental image analysis operations. These operations are required by many computer vision applications. Artificial view-synthesis, 3D scene reconstruction, token tracking and augmented reality are examples of applications that rely heavily on these primitives. The speed and accuracy of such applications rely on the quality of the matching and segmentation. As a result, solutions to these problems have been widely researched. However, due to the difficulty of these problems, there is no universal solution. Most solutions to these two problems make certain assumptions. First, dense matching and image segmentation are often viewed as separate problems. Second, most image segmentation techniques operate on only a single image. This introduces a technique that simultaneously performs image segmentation and dense matching of planar surfaces in a stereo pair of images. Using three matched points from an arbitrary plane, and four other matched points, a projective mapping, known as a homography, is calculated. This homography is used to iteratively grow a region in both images. The result is a matched and segmented plane. Practical tests comparing the computation time of this method to traditional matching techniques are presented. These results are used to motivate the use of the planar technique as a primary step for reducing the overall computation time for dense matching and image segmentation. Source: Masters Abstracts International, Volume: 41-04, page: 1116. Adviser: Bubaker Boufama. Thesis (M.Sc.)--University of Windsor (Canada), 2002.
O'Connell, David John., "Dense matching and image segmentation using projective geometry." (2002). Electronic Theses and Dissertations. 1631.