基于局部感知的点云语义分割方法

Point Cloud Semantic Segmentation Method Based on Local Perception

点云语义分割技术是点云数据处理、三维场景理解与分析的有效手段之一。针对点云场景中局部形态各异,导致网络模型识别特征困难的问题,提出了邻域分布关系学习和混合尺度融合的方法,来增强局部感知能力。在卷积算子思想的基础上,根据邻域内所有点在三个坐标轴方向上的联合分布,学习其在高维特征层面的关系,从而捕获局部的整体相关性。此外,将包含小范围底层特征和大范围深层特征的邻域进行整体融合,有效保留不同层级的特征,并能够辅助网络修正相似或错误特征。在场景分割数据集S3DIS、ScanNet上进行实验验证,结果表明该方法在总体精度和类均精度的评价指标上均有提升,证明了其有效性。

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 S3DIS and ScanNet,the results show that the method has improved in both overall and class-average accuracy evaluation metrics,proving its effectiveness.