This thesis shows how to detect boundaries on the basis of motion information alone. The detection is performed in two stages: (i) the local estimation of motion discontinuities and of the visual flowsfield; (ii) the extraction of complete boundaries belonging to differently moving objects. For the first stage, three new methods are presented: the "Bimodality Tests,'' the "Bi-distribution Test,'' and the "Dynamic Occlusion Method.'' The second stage consists of applying the "Structural Saliency Method,'' by Sha'ashua and Ullman to extract complete and unique boundaries from the output of the first stage. The developed methods can successfully segment complex motion sequences.
Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6814 |
Date | 01 May 1990 |
Creators | Spoerri, Anselm |
Source Sets | M.I.T. Theses and Dissertation |
Language | en_US |
Detected Language | English |
Format | 98 p., 6011802 bytes, 4691342 bytes, application/postscript, application/pdf |
Relation | AITR-1275 |
Page generated in 0.0067 seconds