Study on the 3D point cloud semantic segmentation method of fusion semantic edge detection

Abstract

With the continuous development of deep learning, semantic segmentation, as the basis of 3D scene understanding, has also been widely used in 3D point clouds. Semantic segmentation based on the point cloud has obvious advantages due to its rich data. Aiming at the problems of unclear segmentation target and unclear edge in point cloud semantic segmentation, a 3D point cloud semantic segmentation algorithm integrating edge detection was proposed. Firstly, complete global semantic features are obtained by the mainstream 3D point cloud semantic segmentation framework. Then, semantic edge detection is used to extract edge semantic features from the point cloud. Finally, the fusion module fuses the semantic features belonging to the same object to make the segmentation target more accurate. In addition, a dual semantic loss function is used to produce semantic segmentation results with better boundaries. Experimental results show that the improved algorithm has better precision than KPConv in S3DIS and ScanNet datasets and better segmentation performance.