Point cloud semantic segmentation technique is one of the effective means for point cloud processing and 3D scene understanding and analysis.For the problem that the local morphology in point cloud scenes varies,which made it difficult for network model to recognize features,the method of neighborhood distribution relationship learning and mixed-scale fusion was proposed to enhance local perception.The idea of convolution operator is adopted,and then the correlation of high-dimensional features was learned based on the joint distribution relationship of all points in the neighborhood in the xyz directions to capture the overall local correlation.In addition,neighborhood fusion of a small range of underlying features and a large range of deep features effectively preserved the advantages of each part and assists the network in correcting similar or erroneous features.Finally the network architecture was established for the semantic segmentation task.Experiments were conducted on the datasets S3 DIS and ScanNet,the results show that the method has improved in both overall and class-average accuracy evaluation metrics,proving its effectiveness.
关键词
三维场景/点云语义分割/卷积算子/局部感知
Key words
3D scenes/point cloud semantic segmentation/convolutional operators/local perception
维普
万方数据