Title :
Trinocular Cooperative Stereo Vision and Occlusion Detection
Author :
Mingxiang, Li ; Yunde, Jia
Author_Institution :
Sch. of Comput. Sci. & Eng., Beijing Inst. of Technol., Beijing
Abstract :
In this paper, we present a cooperative stereo vision algorithm with three cameras for dense disparity mapping and occlusion detection. Based on nonlinear iteration and multiple cameras, the disparity maps are smooth and the object boundaries are accurate. Occlusions for each stereo pair are detected effectively by examining the iterative inhibition and magnification of the matching evaluation.
Keywords :
cameras; feature extraction; iterative methods; stereo image processing; dense disparity mapping; disparity maps; multiple cameras; nonlinear iteration; occlusion detection; trinocular cooperative stereo vision; Cameras; Computer vision; Costs; Dynamic programming; Iterative algorithms; Optimization methods; Robot kinematics; Stereo vision; Transforms; Transmission line matrix methods; Cooperative Matching; Multiple Cameras; Occlusion Detection; Stereo Vision;
Conference_Titel :
Robotics and Biomimetics, 2006. ROBIO '06. IEEE International Conference on
Conference_Location :
Kunming
Print_ISBN :
1-4244-0570-X
Electronic_ISBN :
1-4244-0571-8
DOI :
10.1109/ROBIO.2006.340087
