A Fast Foveated Stereo Matcher

摘要

A stereo-matcher is required to form part of an active vision system currently under construction. Previous approaches to accomplishing the task of computing binocular disparity quickly have included the use of dedicated hardware and a tradeoff of speed against pixel resolution. A software-based stereo-matcher is reported which produces results quickly whilst retaining sub-pixel accuracy. The process of foveation is applied to a scale-space matching algorithm to produce disparity maps of spatially non-linear resolution. Results are presented evaluating the accuracy of the algorithm and also runtime performance of a Java-based implementation executing on standard hardware.