A Improved Stereo Matching Fast Algorithm Based on Dynamic Programming
Compared with the local algorithm in stereo matching,the high quality disparity space image is calculated by the global algorithm,which is difficult to use in practical application for its long computation time.The dynamic programming is one of the global algorithms with a fast matching speed,but it has strip blemish in matching result.In this paper,a new dynamic programming based method is proposed to accelerate the matching speed and improve the matching quality.Firstly,the color feature of two images are calculated using the Laplacians of Gaussian pyramid algorithm,and the color feature of the image pair obtained are matched.Secondly,the matching points are taken as the ground control points of the scan line,which is cut into several short line segments.Finally,all line segments are matched to obtain the disparity of the scan line.The experimental results show that the matching speed is accelerated greatly with improved disparity image quality.
Stereo Matching Global Optimize Algorithm Image Pyramids Dynamic Programming
Zi Wei Zhou
School of Electronics &Information, Liaoning University of Science and Technology, Anshan 114002 China
国际会议
广州
英文
657-661
2012-11-16（万方平台首次上网日期，不代表论文的发表时间）