Regular Paper

[OPTICAL REVIEW Vol. 21, No. 6 (2014) 826-832]
© 2014 The Japan Society of Applied Physics

A Stereo Matching in Complex Scene and Occlusion Handling Model

Xing PANG, Yi ZHANG, Jing HAN, and Lian-fa BAI*

Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing 210094, China

(Received April 29, 2014; Accepted August 26, 2014)

An algorithm is proposed which the tree structure of dynamic programming with self-adaptive parameters and a disparity iterative refinement to improve stereo matching performance. The algorithm model consists of an initialization model and a disparity iterative refinement. To obtain the initial disparity map with “clear” background and whole details, the tree structure of dynamic programming with self-adaptive parameters is presented. A disparity iterative refinement is proposed to estimate the disparity of unreliable pixels in the doubtful regions. The disparity iterative refinement consists of a doubtful regions growing method and a disparity filling based on color similarity. The results of experiment evaluated with Middlebury data sets show that our algorithm can effectively ameliorate “fatting inflating” by occlusion and obtains a high quality of disparity map.

Key words: the tree structure of dynamic programming, self-adaptive parameters, a disparity iterative refinement, a doubtful regions growing method, a disparity filling


*E-mail address: mrblf@163.com

 

© 1994-2014 The Japan Society of Applied Physics
Produced, Developed, and Maintained by The Optical Society of Japan (An Affiliate of the Japan Society of Applied Physics)
Printed in Japan by Komiyama Printing Co., Ltd.

mail to Editorial Office, OPTICAL REVIEW