Real-time GPU-based local stereo matching method

Jinglin Zhang, Jean-François Nezan, Maxime Pelcat, Jean-Gabriel Cousin

Abstract: Stereo matching techniques aim at reconstruct the disparity maps with a pair of images. This paper propose a real-time stereo matching algorithm optimized for GPU platform. Our method first constructs the matching cost by combining measure of truncated absolute difference (TAD) cost and census cost; then we aggregates matching costs using adaptive weight method and iterates with square step size in the horizontal and vertical pass. In addition, we implement our algorithm on GPU platform using a high level compiler HMPP (Hybrid Multicore Parallel Programming) which greatly reduces the development time and make use of the parallel computing of GPU device with CUDA (Compute Unified Device Architecture)/OpenCL (Open Computing Language). The GPU-based implementation of our method obtains 20 fps on a general laptop's GPU satisfying real-time requirement.