DocumentCode :
3252207
Title :
A neural computational scheme for extracting optical flow from the Gabor phase differences of successive images
Author :
Tsao, Tien-Ren ; Chen, Victor C.
Author_Institution :
Vitro Corp., Silver Spring, MD, USA
Volume :
4
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
450
Abstract :
The authors propose a neurobiologically plausible representation of the Gabor phase information, and present a neural computation scheme for extracting visual motion information from the Gabor phase information. The scheme can compute visual motion accurately from a scene with illumination changes, while other neural schemes for optical flow must assume stable brightness. The computational tests on synthetic and natural image data showed that the scheme was robust to the natural scenes. An architecture is presented of a neural network system based on the Gabor phase representation of visual motion
Keywords :
motion estimation; neural nets; Gabor phase differences; Gabor phase information; illumination changes; natural image data; neural network; neurobiologically plausible representation; optical flow; successive images; visual motion information; Brightness; Computer architecture; Data mining; Image motion analysis; Layout; Lighting; Neural networks; Optical computing; Robustness; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227303
Filename :
227303
Link To Document :
بازگشت