Title :
A new method for stereo matching problem in computer vision using synergetics
Author :
Maeda, Hiroshi ; Okada, Satoshi ; Irie, Takasuke
Author_Institution :
Dept. of Comput. Eng., Kyushu Inst. of Technol., Kitakyushu, Japan
fDate :
6/21/1905 12:00:00 AM
Abstract :
This paper presents a new method based on synergetics for a stereo matching problem including occlusion. The method constructs two kinds of parameters, called order parameter and attention parameter. The matching process between a left image and a right image is represented by differential equations with the two kinds of parameters, which describe a self-organization dynamics based on synergetics. The attention parameters greatly influence the decision of the correspondence between two images. Accordingly, a key point of the proposed method is how to construct the two kinds of parameters. The method is applied to stereo matching using building blocks
Keywords :
computer vision; differential equations; image matching; stereo image processing; attention parameter; building blocks; computer vision; differential equations; image correspondence; left image; occlusion; order parameter; right image; self-organization dynamics; stereo matching problem; synergetics; Computational efficiency; Computer vision; Concurrent computing; Control systems; Differential equations; Dynamic programming; Fluctuations; Force control; Mathematical model; Stereo vision;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.823257
