Stereo Vision Robot Obstacle Detection Based on the SIFT

Abstract

This paper presents a method of binocular vision obstacle detection based on SIFT feature matching algorithm. First, a model of depth measurement based on stereo vision is built, it does not require resume the three-dimensional coordinate of spatial point under the world coordinate system. According to the characteristics of the model, we proposed the binocular stereo vision calibration method based on parallel optical axis, Finally, the pixel coordinates of matching points are extracted with SIFT feature matching algorithm and completed the distance detection of the obstacle. The experimental results demonstrated the feasibility and effectiveness of the method.