面向部件分割的PointNet注意力加权特征聚合网络  

Attention weighted feature aggregation PointNet network for part segmentation

作　　者：梁振华 王丰 Liang Zhenhua;Wang Feng(School of Information Engineering,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学信息工程学院,广州510006

出　　处：《计算机应用研究》2023年第5期1571-1576,1582,共7页Application Research of Computers

基　　金：国家自然科学基金资助项目(61901124);广东省自然科学基金资助项目(2021A1515012305);广州市基础研究计划资助项目(202102020856)。

摘　　要：为解决PointNet最大池化损失次要特征导致部件分割精度降低的问题,提出一种面向部件分割的PointNet注意力加权特征聚合网络,能够充分利用点云的不同特征进行部件分割。首先利用多层感知机提取点云的空间几何特征,将特征乘以共享权重矩阵,以获取每个点的每一个特征的注意力分数;接着把归一化的分数作为权重乘以对应的全局特征并求和,得到聚合的全局特征;最后使用多层感知机将聚合的特征映射到部件分割结果。实验结果表明,相比于传统PointNet方法,该方法提升了部件分割的总平均交并比,同时在网络鲁棒性和计算复杂度方面具有显著优势,有效优化了PointNet。In order to solve the problem of reducing the accuracy of part segmentation due to the loss of secondary features by PointNet max pooling,this paper proposed attention weighted feature aggregation PointNet network for part segmentation,and it could make full use of different features of point cloud for part segmentation.Firstly,it used the multiple layer perceptrons to extract the spatial geometric features of the point cloud,and then multiplied the features and the shared weight matrix to obtain the attention scores of each feature of each point.Then it used the normalized scores as the weight to multiply the corresponding global feature and summed to obtain the aggregated global feature.Finally,it used the multiple layer perceptrons to map the aggregated feature to the part segmentation results.Experimental results show that the proposed method improves the overall average mean intersection over union of part segmentation than traditional PointNet,has significant advantages in network robustness and computational complexity,and effectively optimizes PointNet.

关 键 词：机器视觉 点云 部件分割 注意力机制 特征聚合 鲁棒性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]