基于自适应聚合的立体视觉合作算法tf-软件学报.pdfVIP

ISSN 1000-9825, CODEN RUXUEW E-mail: jos@ Journal of Software , Vol.19, No.7, July 2008, pp.1674− 1682 DOI: 10.3724/SP.J.1001.2008.01674 Tel/Fax: +86-10 © 2008 by Journal of Software . All rights reserved. ∗ T F 基于自适应聚合的立体视觉合作算法 + 李鸣翔P P , 贾云得 (北京理工大学 计算机科学技术学院,北京 100081) Adaptive Aggregation Based Cooperative Stereo Vision + LI Ming-XiangP P , JIA Yun-De (School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China) + Corresponding author: E-mail: {lmx,jiayunde}@ Li MX, Jia YD. Adaptive aggregation based cooperative stereo vision. Journal of Software, 2008,19(7): 1674−1682. /1000-9825/19/1674.htm Abstract : This paper proposes a stereo vision cooperative algorithm for high quality dense disparity mapping. This algorithm iteratively performs the local adaptive aggregation and inhibitive magnification based on the morphologic similarity with adaptive weight, and generates high quality dense disparity map effectively. This paper also extends the cooperative algorithm to trinocular stereo vision system. By rebuilding the camera coordinate system, the trinocular images are rectified, and the support area and trinocular inhibition area are established in disparity space based on the continuity and uniqueness constrains. Experimental results show that the trinocular stereo vision cooperative algorithm can generate accurate real dens