针对现有点云分类与分割方法使用最大池化聚合局部邻域特征,导致最大值以外的重要信息丢失的缺陷,提出一种结合自适应图卷积 AdaptConv 和注意力池化 AP 的点云分类与分割网络.首先,采用K 近邻算法构建点云局部图结构,根据点的特征生成自适应卷积核,灵活精确地捕获点云的局部邻域特征;其次,为有效提高特征聚合能力,采用注意力池化定义能量函数得到权重值,加权并聚合出更具代表性的点云局部特征;最后,堆叠自适应图卷积和注意力池化逐层提取全局特征,提高网络的分类和分割精度.实验结果表明,相较基准方法,点云分类的平均类别精度提升 0.9%,部件分割和语义分割的平均交并比分别提升 0.8%和 0.3%,证明所提方法可有效提升点云分类与分割的准确率,具有较高的鲁棒性.
Point cloud classification and segmentation based on adaptive graph convolution and attention pooling
In response to the limitation of existing point cloud classification and segmentation meth-ods that use max pooling to aggregate local neighborhood features,which leads to the loss of important information beyond the maximum value,this paper proposes a point cloud classification and segmenta-tion network that combines Adaptive Graph Convolution(AGConv)and Attention Pooling(AP).First-ly,a local graph structure of the point cloud is constructed using K-nearest neighbors algorithm,and a-daptive convolution kernels are generated based on the features of the points,enabling flexible and accu-rate capturing of local neighborhood features.Secondly,to effectively enhance feature aggregation,at-tention pooling is utilized to define an energy function and obtain weight values,which are used to weight and aggregate more representative local features of the point cloud.Finally,adaptive graph con-volution and attention pooling are stacked to extract global features layer by layer,thereby improving the accuracy of classification and segmentation.Experimental results demonstrate that compared with the benchmark network,the average class accuracy of point cloud classification is improved by 0.9%,and the average intersection over union of part segmentation and semantic segmentation is improved by 0.8%and 0.3%respectively.This demonstrates that the algorithm can effectively improve the accuracy of point cloud classification and segmentation,and has high robustness.
万方数据
维普
