A Stereo Matching Approach to Detect Obstacle in ALV System

Abstract

In ALV system based on stereo vision, the obstacle detection is one of the most important problems. In this paper, an algorithm is proposed based on moment invariant to detect obstacle in ALV system. Firstly, a simple method is applied to binarize the images by the defined binarization function; Secondly, the binarized images are segmented using outer contour tracing algorithm and regions of left and right images are detected respectively; Lastly, the regions are matched between left and right image, the successful matched regions are the likely obstacle. Stereo pairs captured from ALV system are used to test the proposed algorithm, the result indicate that the approach is valid and feasible.