Semantic segmentation of point clouds by fusing dual attention mechanism and dynamic graph convolution

The existing semantic segmentation methods of 3D point clouds based on deep learning usually ignore the profound semantic information between neighboring points when extracting local features and fail to consider the useful information in other neighboring features when aggregating local neighboring features. To solve these problems, a semantic segmentation algorithm of 3D point clouds fusing dual attention mechanism and dynamic graph convolution neural network (DGCNN) was proposed. Firstly, edge features were constructed by dynamic graph convolution operation, and the relative distance between the center point and the neighboring points was input to the kernel point convolution operation to obtain enhanced edge features, further strengthening the relationship between the center point and the neighboring points. Secondly, the spatial attention module was introduced to establish the dependence between neighboring points, and the similar feature points were intercorrelated, so as to extract profound context information in the local neighborhood and enrich the geometric features of neighboring points. Finally, the channel attention module was introduced when local neighboring features were aggregated. By giving different weights to different channels, the purpose of enhancing useful channels and suppressing useless channels was achieved, so as to improve the accuracy of semantic segmentation. The experimental results on the S3DIS dataset and SemanticKITTI dataset show that the semantic segmentation accuracy of this algorithm has reached 66.0% and 59.4%, respectively. Compared with other classical network models, this algorithm has achieved a better point cloud segmentation effect. © 2024 Beijing University of Aeronautics and Astronautics (BUAA). All rights reserved.