摘要
针对现有方法在处理局部特征时忽略方向信息,且由于卷积核大小的限制无法有效地提取点云邻域特征等问题,提出一种点云分割方法.首先结合方向编码和空洞采样最大程度扩大网络的局部感受野.其次利用图卷积神经网络挖掘局部邻域内点的信息.然后使用邻域特征提取层自动加权融合邻域特征为更具有代表性的单个特征点.最后结合空间注意力机制,增加远程点之间的联系.在S3DIS数据集上进行物体分割实验的结果表明,所提方法的OA和mIoU比PointWeb高1.3个百分点和4.0个百分点,比基线方法 RandLA-Net高0.6个百分点和0.7个百分点,使用空洞采样与方向编码能够有效地提高点云的语义分割精度.
To address the problem that existing methods ignore directional information when processing local features and cannot effectively extract point cloud neighborhood features due to the limitation of convolutional kernel size,this paper proposes a point cloud segmentation method.Firstly,by combining directional encoding and hole convolution,the local receptive field of the network is maximized.secondly,graph convolutional neural networks are utilized to mine information within local neighborhoods of points.subsequently,a neighborhood feature extraction layer is employed to automatically weight and fuse neighborhood features into a more representative single feature point.finally,in conjunction with a spatial attention mechanism,the connections between distant points are enhanced.The results of object segmentation experiments on the S3DIS dataset show that the OA and mIoU of the proposed method are,respectively,1.3 percentage points and 4.0 percentage points higher than PointWeb,0.6 percentage points and 0.7 percentage points higher than the baseline method RandLA-Net,and the use of hole sampling and directional coding can effectively improve the semantic segmentation accuracy of point clouds.
作者
李彭
陈西江
赵不钒
宣伟
邓辉
Li Peng;Chen Xijiang;Zhao Bufan;Xuan Wei;Deng Hui(School of Safety and Emergency Management,Wuhan University of Technology,Wuhan 430070;School of Civil Engineering and Architecture,Wuhan University of Technology,Wuhan 430070)
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2024年第7期1014-1025,共12页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金(42171428)。
关键词
三维点云
空洞采样
物体分割
注意力机制
方向编码
3D point cloud
hole sampling
object segmentation
attention mechanism
directional coding
