Real-Time Neighborhood Based Disparity Estimation Incorporating Temporal Evidence

This paper presents a system for dense area based disparity estimation from binocular rectified image sequences with the integration of temporal evidence. The system is using dense 2D optical flow fields and timely displaced disparity estimates to reason about the observed 3D scene flow. This scene flow is then exploited to strengthen timely consistent observations in the disparity estimation. Moreover a novel neighborhood assumption is presented, which allows to seamlessly implement the presented algorithm on the GPU. It is shown that by means of the presented approach the sensitivity to noise and ambiguities observed with plain real-time disparity estimations can be improved, even in fully dynamic scenarios with simultaneous movement of objects and cameras.