Affiliation:
1. School of Safety Science and Emergency Management Wuhan University of Technology Wuhan China
2. Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of Ministry of Natural Resources East China University of Technology Nanchang China
3. School of Surveying and Mapping Engineering East China Institute of Technology Nanchang China
Abstract
AbstractMost existing point cloud segmentation methods ignore directional information when extracting neighbourhood features. Those methods are ineffective in extracting point cloud neighbourhood features because the point cloud data is not uniformly distributed and is restricted by the size of the convolution kernel. Therefore, we take into account both multiple directions and hole sampling (MDHS). First, we execute spherically sparse sampling with directional encoding in the surrounding domain for every point inside the data to increase the local perceptual field. The data input is the basic geometric features. We use the graph convolutional neural network to conduct the maximisation of point cloud characteristics in a local neighbourhood. Then the more representative local point features are automatically weighted and fused by an attention pooling layer. Finally, spatial attention is added to increase the connection between remote points, and then the segmentation accuracy is improved. Experimental results show that the OA and mIoU are 1.3% and 4.0% higher than the method PointWeb and 0.6% and 0.7% higher than the baseline method RandLA‐Net. For the indoor point cloud semantic segmentation, the segmentation effect of the proposed network is superior to other methods.
Funder
National Natural Science Foundation of China
Reference35 articles.
1. Background‐aware 3‐D point cloud segmentation with dynamic point feature aggregation;Chen J.;IEEE Transactions on Geoscience and Remote Sensing,2022
2. RGAM: A novel network architecture for 3D point cloud semantic segmentation in indoor scenes