Translator Disclaimer
13 March 1996 Multistage affine parameter clustering for improved motion segmentation
Author Affiliations +
Proceedings Volume 2666, Image and Video Processing IV; (1996) https://doi.org/10.1117/12.234737
Event: Electronic Imaging: Science and Technology, 1996, San Jose, CA, United States
Abstract
We propose two key modifications to a recent motion segmentation algorithm developed by Wang and Adelson, which greatly improve its performance. They are: (i) the adaptive k- means clustering step is replaced by a merging step, whereby the hypothesis (affine parameters of a block) which has the smallest representation error, rather than the respective cluster center is used to represent each layer, and (ii) we implement it in multiple stages, where pixels belonging to a single motion model are labeled at each stage. Performance improvement due to the proposed modifications is demonstrated on real video clips.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Georgi D. Borshukov, Gozde Bozdagi, Yucel Altunbasak, and A. Murat Tekalp "Multistage affine parameter clustering for improved motion segmentation", Proc. SPIE 2666, Image and Video Processing IV, (13 March 1996); https://doi.org/10.1117/12.234737
PROCEEDINGS
8 PAGES


SHARE
Advertisement
Advertisement
Back to Top