Lidar Point Semantic Segmentation Using Dual Attention Mechanism

A large amount of environmental point cloud data can be provided by light detection and ranging (LiDAR) sensors. The raw points collected by the LiDAR is disordered and unstructured. It is a challenge to design algorithms to extract features from the raw points. In this paper, we propose the LiDAR point semantic segmentation net (LPSS Net), which is a dual-attention mechanism point cloud segmentation algorithm. First, the LPSS Net extracts point cloud features from the raw points, which uses the self-attention mechanism in the transformer mechanism. Second, in order to suppress irrelevant information in the features and focus on essential information, we propose a novel strategy, which designs a 3D channel attention mechanism in the encoding part. Finally, we demonstrate the applicability of the algorithm by extensive experiments conducted on Semantic3D and SemanticKITTI. A high OA of 90.6% and a mIoU of 71.5% on the Semantic3D data set indicate the feasibility of the algorithm.