Share Email Print
cover

Proceedings Paper

Stereo matching algorithm using wavelet transform
Author(s): Cun Xie; Jia-sheng Hu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Stereo matching is an important and necessary technique for stereo vision. It is usually not good practice to try to find corresponding points for all pixels, and feature points are selected so that unambiguous matches might be obtained. Meantime, in order to reduce the computational cost of finding correspondence, multistage matching is often applied. Wavelet transform has good multi-resolution representation. Using zero- crossing points of wavelet transform coefficients as the features, the corresponding features in a pari of images are found by decomposing images into several levels (multi-scale analysis). So disparity estimation and error exclusion can be finished simultaneously. The efficiency of this algorithm is increased. Finally, the given algorithm is tested on stereo image pairs.

Paper Details

Date Published: 9 October 2000
PDF: 5 pages
Proc. SPIE 4221, Optical Measurement and Nondestructive Testing: Techniques and Applications, (9 October 2000); doi: 10.1117/12.402625
Show Author Affiliations
Cun Xie, Dalian Univ. of Technology (China)
Jia-sheng Hu, Dalian Univ. of Technology (China)


Published in SPIE Proceedings Vol. 4221:
Optical Measurement and Nondestructive Testing: Techniques and Applications

© SPIE. Terms of Use
Back to Top