Asynchronous stereo vision system for front-vehicle detection

摘要

This study uses two low-cost and compact CMOS cameras to construct an asynchronous binocular system and proposes an effective real-time front-vehicle detection algorithm with the binocular system. The proposed vehicle detection algorithm uses the edge information to detect the region of each front vehicle, and then computes the disparities of the front vehicles by an adaptive search method. According to the disparity values, the relative distances between the front and the host vehicles can be computed. The proposed algorithm of the manuscript conquers the asynchronous exposure problem and cost issue of a binocular system. Experimental results show that the proposed system can robustly and accurately detect obstacles or other vehicles in real time under different illumination and road conditions.