基于K最近邻局部点关系图卷积的点云分类

Point Cloud Classification Based on K-nearest Neighbor Local Point Relation Graph Convolution

为进一步提高大规模多种类三维点云分类的准确率,提出一种局部区域建立K近邻点关系的卷积神经网络,其关键是从点与点的关系中进行学习。在采样组采样后,对点云模型进行建图,从点与点之间的关系以及中心点的特征进行更深一步的关系学习,从而进行点云的分类工作。由于是从局部的特征整合到整体,使得该方法对形状感知敏感并具有鲁棒性。最终的试验结果表明,该算法在公开数据集ModelNet40上的准确率达到92.5%。与现有的三维点云分类算法相比,其能够更有效地整合局部特征和全局特征,从而能进一步提高三维点云模型分类的准确性。

In order to further improve the accuracy rate of large-scale and various kinds of 3 D point clouds,this paper proposes a Convolutional Neural Network(CNN)that builds a relationship of K-nearest neighbor graphs in a local area.The key is to learn the relation between points.After the sample group finished sampling,the point cloud model is constructed and the point cloud is classified through learning the profound relationship between points and characteristics of the central point.Because this method integrated from the partial to the whole features,it makes this method to be sensitive to the shape and robust.The final experiment demonstrates that the precision rate of this method reached 92.5%on the public data set ModelNet40.Compared with the existing 3 D point cloud classification algorithms,this algorithm could integrate local features and global features more effectively.Therefore,it will further increase the accuracy of 3 D point cloud model classification.