Research and implementation of adaptive stereo matching algorithm based on ZYNQ

Stereo matching is an important method in computer vision for simulating human binocular vision to acquire spatial distance information. Implementing high-precision and real-time stereo-matching algorithms on hardware platforms with limited resources remains a significant challenge. Although the semi-global stereo-matching algorithm strikes a good balance between obtaining accuracy in the disparity map and computational complexity, it uses a fixed window for matching, resulting in lower matching accuracy in image regions with depth discontinuities and weak textures. To address the shortcomings of existing semi-global stereo-matching algorithms, an adaptive window semi-global stereo-matching algorithm is proposed, along with post-processing disparity optimization through left–right consistency check and median filtering. On test images provided by the Middlebury dataset, the average matching accuracy improved by 5.07% compared to traditional-matching algorithms. This algorithm is implemented on a Zynq UltraScale + chip, utilising 42,072 LUTs, 66,532 registers, and 101 BRAMs for the entire stereo-matching architecture. For images with a resolution of 1280 × 720 and 64 disparity levels, the final-processing speed can reach 54.24 fps.