Fast Stereovision with Subpixel-Precision

Abstract

A fast stereo algorithm based on aliasing effects of simple disparity estimators within a coherence detection scheme is presented. The algorithm calculates dense disparity maps with subpixel-precision by performing local spatial filter operations and simple arithmetic transformations. Performance similar to classical area-based approaches is achieved, but without the complicated hierarchical search structure typical for these approaches. The algorithm is completely parallel; the disparity valves are calculated independently for each pixel. In addition, local validation counts for the disparity estimates and a fused cyclopean view of the scene are available within the proposed network structure for coherence-based stereo.