| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 1.31 MB | Adobe PDF |
Advisor(s)
Abstract(s)
This paper describes an approach for integrating motion estimation and region clustering techniques with the purpose of obtaining precise multiple motion segmentation. Motivated by the good results obtained in static segmentation we propose a hybrid approach where motion segmentation is achieved within a region-based clustering approach taken the initial result of a spatial pre-segmentation and extended to include motion information. Motion vectors are first estimated with a multiscale variational method applied directly over the input images and then refined by incorporating segmentation results into a region-based warping scheme. The complete algorithm facilitates obtaining spatially continuous segmentation maps which are closely related to actual object boundaries. A comparative study is made with some of the best known motion segmentation algorithms.
Description
Indexado ISI
Keywords
Motion segmentation Motion estimation Clustering
Citation
Monteiro, Fernando C.; Campilho, Aurélio (2008). Region and graph-based motion segmentation. IN Image Analysis and Recognition. Berlin: Springer. p. 609-618, Vol. 5112. ISBN 978-3-540-69811-1