Quantitative evaluation of matching methods and validity measures for stereo vision

The authors present a qualitative and quantitative comparison of various si milarity measures that form the kernel of common area-based stereo-matching systems. The authors compare classical difference and correlation measures as well as nonparametric measures based on the rank and census transforms for a number of outdoor images. For robotic applications, important conside rations include robustness to image defects such as intensity variation and noise, the number of false matches, and computational complexity. In the a bsence of ground truth data, the authors compare the matching techniques ba sed on the percentage of matches that pass the left-right consistency test. The authors also evaluate the discriminatory power of several match validi ty measures that are reported in the literature ftir eliminating false matc hes and for estimating match confidence. For guidance applications, it is e ssential to have an estimate of confidence in the three-dimensional points generated by stereo vision. Finally, a new validity measure, the rank const raint, is introduced that is capable of resolving ambiguous matches for ran k transform-based matching.