Stereo Matching Algorithm for Robot Binocular Images in Real Time

For the problem of acquiring binocular vision depth information on a mobile robot platform, a binocular image stereo matching algorithm was proposed for dynamic image sequence. Firstly, a mature semi-global matching algorithm was adopted to carry out the rapid stereo matches of stereo images for the disparity images. On this basis, the major noises encountered during the stereo match process on a mobile platform in a complex environment were analyzed, including the white-spot noise as well as the fault flicker noise. Further, a white-spot filtering algorithm and a disparity image time-domain filtering algorithm were developed respectively to reject the noises. Finally, the experimental verifications were performed. The results show that, the noises coming from stereo matches of dynamic binocular vision images can be effectively suppressed with the proposed algorithms, besides a continuous and clear disparity image sequence can be derived in real-time, which is significant to the obstacle avoidance and the situational awareness of a running mobile robot in a complicated environment.