RGB-D Road Segmentation Based on Geometric Prior Information

Deep data can provide rich spatial structure information, which can effectively exclude the interference of lighting and road texture in road segmentation. This paper proposes a road segmentation model based on two kinds of a priori knowledge: disparity information, and surface normal vector information. Then, a two-branch neural network is used to process the color image and the processed depth image separately, and an effective fusion module is designed to make full use of the complementary features of the two modalities. The experimental results on the KITTI road detection dataset and Cityscape dataset show that the method in this paper has good road segmentation performance.