Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (24): 140-146.DOI: 10.3778/j.issn.1002-8331.2209-0198

• Pattern Recognition and Artificial Intelligence • Previous Articles     Next Articles

Classified Convolutional Neural Networks for Sparse Point Clouds Regularization Disposing

LI Hengyu, YANG Jiazhi, SHEN Jie, ZHANG Junkai   

  1. 1.College of Information Science and Engineering, Guilin University of Technology, Guilin, Guangxi 541004, China
    2.Guangxi Key Laboratory of Embedded Technology and Intelligent System, Guilin, Guangxi 541004, China
  • Online:2023-12-15 Published:2023-12-15

对稀疏点云规则化处理的分类卷积神经网络

李恒宇,杨家志,沈洁,张峻恺   

  1. 1.桂林理工大学 信息科学与工程学院,广西 桂林 541004
    2.广西嵌入式技术与智能系统重点实验室,广西 桂林 541004

Abstract: As one of the important methods of point cloud classification, deep learning usually fails to fully extract local spatial correlation due to the sparsity, disorder and limitation of point cloud. Directly using convolution to extract relevant features of points will lead to the loss of feature information. To this end, this paper proposes a convolutional neural network based on X-transform (XTNet) for point cloud classification. Firstly, XTNet performs X-transform on the input original point cloud data and replaces them into a potential canonical order, which suppresses the influence of point cloud disorder and sparsity on convolution operation and avoids information loss during convolution operation. Then, the [K] nearest neighbor algorithm is used to construct the local region, and the convolution layer is used to extract the local information. Secondly, while extracting local features, channel expansion is used to increase information transmission and enrich features. Finally, skip connections are set between each local feature extraction module to further reduce the loss of local information. In this paper, experiments are carried out in the standard public dataset ModelNet40 and the real dataset ScanObjectNN. Experimental results show that compared with the current mainstream multiple high-performance networks, the classification accuracy of XTNet is improved by 0.3~4 percentage points, and it has good robustness and universality.

Key words: deep learning, point cloud classification, convolutional neural network

摘要: 深度学习作为点云分类的重要方法之一,通常会因为点云的稀疏性、无序性、有限性等特点,导致卷积算子不能充分提取局部空间相关性,直接使用卷积提取点的相关特征将导致特征信息的丢失。为此提出一种经过X变换后的点云分类卷积神经网络:XTNet(convolutional neural network based on X-transform)。XTNet对输入的原始点云数据进行X变换,将它们置换成潜在的规范顺序,抑制点云无序性、稀疏性对卷积操作的影响,避免卷积操作过程中的信息丢失;使用[K]近邻算法构建局部区域后,使用卷积层提取局部信息;在提取局部特征的同时通过通道扩充增加信息传递、丰富特征;在各局部特征提取模块间设置跳跃连接,进一步减少局部信息的丢失。在标准公开数据集ModelNet40和真实数据集ScanObjectNN中进行了实验。实验结果表明,与目前主流的多个高性能网络相比,XTNet分类准确率提高了0.3~4个百分点,并且拥有良好的鲁棒性和普适性。

关键词: 深度学习, 点云分类, 卷积神经网络