基于图注意力机制的三维点云感知
3D point cloud perception based on graph attention mechanism
高瑞贞 1王诗浩 1王皓乾 1张京军 1李志杰2
作者信息
- 1. 河北工程大学机械与装备工程学院,河北邯郸 056038
- 2. 河北新兴铸管股份有限公司,河北邯郸 056300
- 折叠
摘要
基于PointNet++网络的三维点云感知方法能够通过提取目标的几何特征信息来对目标进行分类.虽然PointNet++网络能够提取到点云数据的局部特征,但未考虑点与其邻域点之间的关系,因此一旦缺失一个点的局部特征,网络的性能会受到较大的影响.针对这一问题,该文提出一种基于图注意力机制(graphic attention mecahnism)的新网络架构GA-PointNet++.模型利用图注意力机制在点与其邻域点之间分配注意力系数,完成点云局部特征的提取.在分类实验中,该文在ModelNet40数据集上的实验结果表明,提出的GA-PointNet++模型最终的平均分类准确率达到了 88.8%,总体准确率达到了 91.3%.相较于PointNet++基线模型总体准确率提高 1.1百分点,验证了GA-PointNet++在分类任务中的有效性.
Abstract
The 3D point cloud perception method based on PointNet++network can classify objects by extracting geometric feature information of objects.Although the PointNet++network can extract the local features of point cloud data,the relationship between points and their neighborhood points is not considered.Thus,once the local feature of a point is missing,the performance of the network will be greatly affected.Aming at solving this problem,a new network architecture based on graphic attention mechanism(GA-PointNet++)is proposed.The model uses the graph attention mechanism to distribute the attention coefficient between points and their neighborhoods points,and extracts the local features finally.In the classification experiment,results on ModelNet40 data set show that the mean class accuracy of the model is 88.8%,and the overall accuracy rate reached 91.3%,improved by 1.1%compare with PointNet++baseline model.The results confirm the effectiveness of the proposed GA-PointNet++model in classification tasks.
关键词
图像处理/深度学习/图注意力机制/邻域点Key words
image processing/deep learning/graph attention mechanism/neighborhood points引用本文复制引用
基金项目
河北省高校科技攻关项目(ZD2018207)
出版年
2024
NETL
NSTL
万方数据