Three-dimensional Ambient Perception Method Based on Binocular Stereo Visual and Structural Light

Abstract

Environmental awareness is a key technology in the study of assisted driving system or unmanned driving technology. Aiming at the problem that the environment perception system is difficult to reconstruct in the complex environment, such as dark light and weak texture, a 3D environment perception method based on binocular stereo vision and structured light was proposed. An improved gray-scale barycenter extraction algorithm was used to extract the center of the grating fringe, and a sweeping grating matching method based on polar constraint was used to match the left and right images. Finally, the three-dimensional information of the grating fringe was obtained. The experimental results show that the center extraction time of a single image is less than 0.5S, and the 3D data of the measured object can be obtained to meet the requirements of the system.