一种考虑法矢量的点云语义分割网络

Point-Cloud Semantic Segmentation Network Considering Normals

在基于深度学习的点云分类任务中,PointNet模型直接以点云的三维坐标作为输入,但其存在着对形状不规则物体的分类效果不理想的问题。在PointNet模型的基础上增加一个法矢量估计的模块,提出一种考虑点云法矢量的语义分割网络。其中,法矢量估计方法采用的是主成分分析方法。实验结果表明,改进模型的总体准确率、平均类别准确度和平均类别交互比相较于原始模型分别提升了2.3个百分点、7.1个百分点和3.9个百分点。13个语义类别中有10个类别的分类效果得到提升,其中对沙发和柱状物的分类准确度分别提升了45.6个百分点和42.2个百分点,平均类别交互比分别提升了19.8个百分点和25.0个百分点。结果表明,考虑法矢量的PointNet网络能够在一定程度上提升网络的整体性能,对沙发和柱状物的分类效果有显著提升。

In deep learning-based point-cloud semantic classification,PointNet considers the three-dimensional coordinates of the point cloud as a direct input,however,the classification of irregular shape objects is a challenge.In this study,we propose a semantic segmentation network considering the normals of point cloud by adding a normal estimation module on PointNet.We estimate the normals using a principal component analysis method.Compared with the original model,the overall accuracy,mean per-class accuracy,and mean per-class intersection-over-union of the improved model are improved by 2.3 percentage points,7.1 percentage points,and 3.9 percentage points respectively.Among the 13semantic classes,the classification accuracy for 10 classes is improved,of which the classification accuracy of sofa and column is improved by 45.6 percentage points and 42.2 percentage points,respectively,and the mean per-class intersection-over-union is improved by 19.8 percentage points and 25.0 percentage points,respectively.Results show that the semantic segmentation network considering normals can improve the overall performance of the network to a certain extent and can significantly improve the classification effect of sofa and column.