DocumentCode :
3316236
Title :
A model of figure-ground segregation from kinetic occlusion
Author :
Chou, George T.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., MIT, Cambridge, MA, USA
fYear :
1995
fDate :
20-23 Jun 1995
Firstpage :
1050
Lastpage :
1057
Abstract :
The paper presents a model of image segmentation that can distinguish foreground from background purely on the basis of motion information. The main processing steps involved are: detection of motion boundaries, and analysis of figure ground relationship. The proposed model utilizes the observation that in kinetic occlusion, motion boundaries typically display mixture motion information, and foreground surfaces tend to move with motion boundaries. Through distributed probabilistic modeling, these constraints can be embedded into computations with efficient network representations. The resulting networks use spatiotemporal Gabor filters as front ends, and are suitable for parallel distributed processing. We demonstrate the application of the model in the decomposition of moving images into surfaces according to depth
Keywords :
distributed algorithms; image segmentation; motion estimation; probability; distributed probabilistic modeling; figure ground relationship; figure-ground segregation; foreground surfaces; image segmentation; kinetic occlusion; mixture motion information; motion boundary detection; motion information; moving image decomposition; network representations; parallel distributed processing; spatiotemporal Gabor filters; Computer networks; Displays; Distributed computing; Embedded computing; Image motion analysis; Image segmentation; Kinetic theory; Motion analysis; Motion detection; Spatiotemporal phenomena;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision, 1995. Proceedings., Fifth International Conference on
Conference_Location :
Cambridge, MA
Print_ISBN :
0-8186-7042-8
Type :
conf
DOI :
10.1109/ICCV.1995.466818
Filename :
466818
Link To Document :
بازگشت