Stereo matching algorithm using wavelet transform

Cun Xie; Jia-sheng Hu

doi:10.1117/12.402625

9 October 2000 Stereo matching algorithm using wavelet transform

Cun Xie, Jia-sheng Hu

Proceedings Volume 4221, Optical Measurement and Nondestructive Testing: Techniques and Applications; (2000) https://doi.org/10.1117/12.402625
Event: Optics and Optoelectronic Inspection and Control: Techniques, Applications, and Instruments, 2000, Beijing, China

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.

Citation Download Citation

Cun Xie and Jia-sheng Hu "Stereo matching algorithm using wavelet transform", Proc. SPIE 4221, Optical Measurement and Nondestructive Testing: Techniques and Applications, (9 October 2000); https://doi.org/10.1117/12.402625

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available