Laser & Optoelectronics Progress, Volume. 59, Issue 8, 0828004(2022)
Semantic Segmentation of Three-Dimensional Point Cloud Based on Spatial Attention and Shape Feature
Existing segmentation methods based on deep learning focus only on the global or local feature extractions of the point cloud; they ignore the shape information and semantic features between points. We propose a multifeature fusion dynamic graph convolutional neural network based on spatial attention to solve the challenges mentioned above. First, on the basis of edge geometric feature extraction, the low-dimensional geometric features of point cloud are mapped to the high-dimensional feature space to obtain the rich shape information. The multilayer perceptron is used to extract the global high-dimensional features of points. Then, a spatial attention mechanism is introduced to extract contextual semantic features between points. Finally, geometric features and high-level semantic information are effectively fused to enrich the representation of global and local features. The proposed network is tested on several public datasets. Experimental results show that the proposed network has achieved superior performance in object classification, part segmentation, and semantic segmentation.
Get Citation
Copy Citation Text
Wen Hao, Hongxiao Wang, Yang Wang. Semantic Segmentation of Three-Dimensional Point Cloud Based on Spatial Attention and Shape Feature[J]. Laser & Optoelectronics Progress, 2022, 59(8): 0828004
Category: Remote Sensing and Sensors
Received: Aug. 2, 2021
Accepted: Sep. 13, 2021
Published Online: Apr. 11, 2022
The Author Email: Hao Wen (haowensxsf@163.com)