Title :
Spatio-temporal motion segmentation via level set partial differential equations
Author :
Mansouri, Abdol-Reza ; Mitiche, Amar ; El-Feghali, Rosario
Author_Institution :
INRS Telecommun., Montreal, Que., Canada
Abstract :
Motion-based segmentation of image sequences is an important problem of image analysis, with numerous applications to image coding and image manipulation. We present a novel algorithm for segmenting image sequences into distinct motion trajectories. This algorithm is expressed as a system of level set partial differential equations which is solved using level set discretization schemes. We provide experimental results on real image sequences with natural and synthetic image motion
Keywords :
image coding; image motion analysis; image segmentation; image sequences; partial differential equations; set theory; distinct motion trajectories; image analysis; image coding; image manipulation; image sequences; level set discretization; natural image motion; partial differential equations; spatio-temporal motion segmentation; synthetic image motion; Computer vision; Image coding; Image motion analysis; Image segmentation; Image sequence analysis; Image sequences; Level set; Motion analysis; Motion segmentation; Partial differential equations;
Conference_Titel :
Image Analysis and Interpretation, 2002. Proceedings. Fifth IEEE Southwest Symposium on
Conference_Location :
Sante Fe, NM
Print_ISBN :
0-7695-1537-1
DOI :
10.1109/IAI.2002.999926
