Object virtual viewing using adaptive tri-view morphing | |
| Author | Pin Chatkaewmanee |
| Call Number | AIT Diss. no.CS-13-01 |
| Subject(s) | Image processing Computer algorithms |
| Note | A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Engineering in Computer Science, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Dissertation ; no. CS-13-01 |
| Abstract | This dissertation proposes a new technique for generating an arbitrary virtual view of an ob- ject of interest given a set of images taken from around that object. The method enables the illusion of a camera viewing the object along an arbitrary path. The algorithm extends Xiao and Shah’s tri-view morphing scheme to work with wide baseline imagery. Our method per- forms feature detection and feature matching across three views then blends the real views into a virtual view. Tri-view morphing by itself is realistic when occlusion across the three views is minimal, but when it is applied to cases of more complex objects and wide base- lines, occlusions lead to significant artifacts. We propose a new adaptive algorithm to solve these problems by 1) segmenting the views into object and background, 2) obtaining fine- grained correspondences across the three views, and 3) constructing, when a border point in one view is occluded in one or two of the other views, a virtual correspondence for that point. Novel views are synthesized using barycentric interpolation, but occluded polygons are automatically eliminated from the interpolation procedure. In an empirical evaluation, we find that our modified tri-view morphing procedure is a dramatic improvement over the original procedure in cases of complex objects imaged with wide baselines. The result is a system allowing smooth and realistic animation of the virtual object over arbitrary viewing paths. |
| Year | 2013 |
| Corresponding Series Added Entry | Asian Institute of Technology. Dissertation ; no. CS-13-01 |
| Type | Dissertation |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Dailey, Matthew N..; |
| Examination Committee(s) | Guha, Sumanta;Afzulpurkar, Nitin;Khan, Sohaib Ahmad; |
| Scholarship Donor(s) | Sripatum University, Thailand; |
| Degree | Thesis (Ph.D.) - Asian Institute of Technology, 2013 |