Multiscale stereopsis via Gabor filter phase response

Author

Chen, Tieh- Yuh ; Bovik, Alan C. ; Super, Boaz J.

Author_Institution

Dept. of Electr. & Comput. Eng., Texas Univ., Austin, TX, USA

Volume

1

fYear

1994

fDate

2-5 Oct 1994

Firstpage

55

Abstract

The most difficult task in stereopsis is to resolve the correspondence problem from a pair of stereo 2-D images. By observing that the perspective projections of 3-D objects can be described as a phase shift issue, we solve the correspondence problem by employing the phase response via multichannel Gabor filters as matching primitive. Our stereo algorithm is biologically motivated and based on a multiscale, coarse-to-fine strategy. This approach produces a dense disparity map without complex feature extraction and interpolation. Results of the algorithm for both synthetic and natural stereo images are presented

Keywords

filtering theory; physiological models; visual perception; Gabor filter phase response; correspondence problem; dense disparity map; matching primitive; multichannel Gabor filters; multiscale coarse-to-fine strategy; multiscale stereopsis; perspective projections; phase response; phase shift issue; stereo 2D images; Cameras; Feature extraction; Gabor filters; Image resolution; Interpolation; Optical imaging; Pixel; Psychology; Retina; Stereo vision;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1994. Humans, Information and Technology., 1994 IEEE International Conference on

Conference_Location

San Antonio, TX

Print_ISBN

0-7803-2129-4

Type

conf

DOI

10.1109/ICSMC.1994.399811

Filename

399811