Title :
OSCAR: object segmentation using correspondence and relaxation
Author :
Galvin, B. ; McCane, B. ; Novins, K.
Author_Institution :
Dept. of Comput. Sci., Otago Univ., Dunedin, New Zealand
Abstract :
We present a robust motion based segmentation system. We combine a novel relaxation based corner tracking system with existing corner tracking techniques to produce corner trajectories that are virtually free of large errors. This technique is used in conjunction with a probabilistic segmentation algorithm to find and track objects in image sequences
Keywords :
image motion analysis; image segmentation; image sequences; optical tracking; probability; relaxation; OSCAR; corner tracking techniques; corner trajectories; correspondence; image sequences; object segmentation; probabilistic segmentation algorithm; relaxation based corner tracking system; robust motion based segmentation system; Object segmentation;
Conference_Titel :
3-D Digital Imaging and Modeling, 1999. Proceedings. Second International Conference on
Conference_Location :
Ottawa, Ont.
Print_ISBN :
0-7695-0062-5
DOI :
10.1109/IM.1999.805357
