Title :
Spatial/joint space-time motion segmentation of image sequences by level set pursuit
Author :
Mansouri, Abdol-Reza ; Mitich, Amar
Author_Institution :
Inst. Nat. de la Recherche Scientifique, INRS, Montreal, Que., Canada
Abstract :
The basic problem we address in this paper is the following. Given a set of sparse point correspondences, how does one obtain a dense motion field and a motion-based segmentation of the image sequence? We propose a novel solution to this problem by formulating it as pursuit in segmentation space. This segmentation is defined by level set evolution equations, allowing changes in segmentation topology.
Keywords :
image segmentation; image sequences; motion estimation; set theory; topology; dense motion field; image sequences; level set evolution equations; level set pursuit; segmentation topology changes; space-time motion segmentation; sparse point correspondences; spatial/joint motion segmentation; Computer vision; Equations; Image converters; Image segmentation; Image sequences; Iterative algorithms; Level set; Motion segmentation; Topology; Video compression;
Conference_Titel :
Image Processing. 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7622-6
DOI :
10.1109/ICIP.2002.1039938