郑州大学学报（工学版）2024，Vol.45Issue(2)：33-41,9.DOI:10.13705/j.issn.1671-6833.2024.02.006
基于图游走和图注意力的点云分类与分割
Point Cloud Classification and Segmentation Based on Graph Walk and Graph Attention
摘要
Abstract
Aiming at the shortage of distance feature and local geometric structure information in feature extraction,a point cloud classification and segmentation network based on graph walk and graph attention was proposed.First-ly,a guided graph walk algorithm was used to supplement additional geometric information and remote feature infor-mation to the whole feature of point cloud.Secondly,the graph attention mechanism was embedded to make the model on the key areas of the point cloud and improve the feature extraction ability of the network.Finally,dis-tance features were extracted from the initial point cloud and embedded into the network as initial residuals to avoid oversmoothing.Point cloud classification experiments were carried out on ModelNet40 dataset and ScanObjectNN dataset,and point cloud component segmentation and point cloud semantic segmentation experiments were carried out on ShapeNetPart dataset and Toronto-3D dataset,respectively.The experiment results showed that,compared with the benchmark network DGCNN,classification accuracy increased by 1.3 percentages and 5.6 percentages,respectively;The segmentation accuracy was improved by 1.2 percentages and 33.1 percentages respectively.Through the robust analysis on ModelNet40-C dataset,it was proved that the proposed network had strong robust-ness.关键词
点云分类/点云分割/图神经网络/图游走/图注意力机制Key words
point cloud classification/point cloud segmentation/graph neural network/graph walk/graph atten-tion mechanism分类
信息技术与安全科学引用本文复制引用
李文举,姬倩倩,沙利业,储王慧,崔柳..基于图游走和图注意力的点云分类与分割[J].郑州大学学报（工学版）,2024,45(2):33-41,9.基金项目
国家自然科学基金资助项目(61903256,61973307) （61903256,61973307）
上海市生物医药科技支撑专项项目(22S31903900) （22S31903900）
