Fast PatchMatch Stereo Matching using Cross-Scale Cost Fusion for Automotive Applications

Due to recent developments of low-cost image sensors and high-performance embedded processing hardware, future cars and automotive systems will increasingly use binocular stereo vision for environmental perception. However, research and development in stereo vision is still ongoing since there are many challenges unsolved. In this paper, we propose a fast and accurate stereo matching algorithm, designed for automotive applications. It convincingly handles real-world scenes containing complex, textureless, and slanted surfaces. To achieve that, we propose an improved PatchMatch stereo algorithm that combines a census-based cost function with Semi-Global Matching optimization integrated in a cross-scale fusion processing scheme. To further accelerate the algorithm, we propose a novel enhancement approach for PatchMatch-based approximation which allows us to skip the random search or at least significantly reduce the number of iterations. Our method is ranked in the upper third of the KITTI benchmark and among the top performers in terms of processing time.