计算机工程与应用2023，Vol.59Issue(24)：140-146,7.DOI:10.3778/j.issn.1002-8331.2209-0198
对稀疏点云规则化处理的分类卷积神经网络
Classified Convolutional Neural Networks for Sparse Point Clouds Regularization Disposing
摘要
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 net-work 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 infor-mation.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.关键词
深度学习/点云分类/卷积神经网络Key words
deep learning/point cloud classification/convolutional neural network分类
信息技术与安全科学引用本文复制引用
李恒宇,杨家志,沈洁,张峻恺..对稀疏点云规则化处理的分类卷积神经网络[J].计算机工程与应用,2023,59(24):140-146,7.基金项目
国家自然科学基金(41961065) （41961065）
广西创新驱动发展专项(桂科AA18118038) （桂科AA18118038）
广西科技基地和人才专项(桂科AD19254002). （桂科AD19254002）
