Grading Test Platform for Stereo Matching Algorithm

A great deal work about stereo matching methods has been done.Such work shows that stereo matching methods generally perform five steps.Step of computing original matching-cost,step of computing candidate matching-cost and step of computing disparity are very important.In the light of this idea,a grading test platform for stereo matching methods is presented.This platform is designed in the environment of VC++6.0.Four type images are taken to control data-transfer.Performance-checking experiments of the test platform show the platform is excellent with clear structure,perfect function,simple and good expansibility.

[1]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[2]  Xin Du,et al.  A simple rectification method for linear multi-baseline stereovision system , 2004, Journal of Zhejiang University. Science.

[3]  Vladimir Kolmogorov,et al.  Computing visual correspondence with occlusions using graph cuts , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[4]  Aaron F. Bobick,et al.  Disparity-Space Images and Large Occlusion Stereo , 1994, ECCV.

[5]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[6]  Takeo Kanade,et al.  A locally adaptive window for signal matching , 2004, International Journal of Computer Vision.