Author： Wu Hsien-Huang Yu Yu-Hua
Publisher： Springer Publishing Company
ISSN： 0921-0296
Source： Journal of Intelligent and Robotic Systems, Vol.42, Iss.1, 2005-01, pp. : 71-94
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
Projective geometry has been proved to be a useful tool for solving the rectification problem without camera calibration. However, if the matrices used for projective rectification (homographies) are not constrained properly, the rectification process can cause great geometric distortion. For visual application, e.g., tele-operation for remotely controlled robot arm, rectification with minimum geometry distortion should be pursued. In this paper, we propose an improved algorithm to minimize the distortion by combining a newly developed projective transform with a properly chosen shearing transform. Experimental data show that our proposed method works quite well for all the image pairs under test. Comparison with other available methods based on visual inspection and numerical data demonstrates the superiority of the new approach.
Related content
Three principles in stereo vision
Advanced Robotics, Vol. 1, Iss. 4, 1986-01 ,pp. :
Access to resources
Recommend
Stereo vision-crossing the Is and dotting the Ts
Industrial Robot: An International Journal, Vol. 21, Iss. 2, 1994-02 ,pp. :
VisionBug: A Hexapod Robot Controlled by Stereo Cameras
By Chow Y.H.
Autonomous Robots, Vol. 13, Iss. 3, 2002-11 ,pp. :