Classified Convolutional Neural Networks for Sparse Point Clouds Regularization Disposing

doi:10.3778/j.issn.1002-8331.2209-0198

Abstract

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

LI Hengyu, YANG Jiazhi, SHEN Jie, ZHANG Junkai. Classified Convolutional Neural Networks for Sparse Point Clouds Regularization Disposing[J]. Computer Engineering and Applications, 2023, 59(24): 140-146.

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.

References

[1] 李娇娇，孙红岩，董雨，等.基于深度学习的3维点云处理综述[J].计算机研究与发展，2022，59（5）：1160-1179.
LI J J，SUN H Y，DONG Y，et al.Survey of 3-dimensional point cloud processing based on deep learning[J].Journal of Computer Research and Development，2022，59（5）：1160-1179.
[2] GUO Y，WANG H，HU Q，et al.Deep learning for 3d point clouds：a survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，43（12）：4338-4364.
[3] 文沛，程英蕾，余旺盛.基于深度学习的点云分类方法综述[J].激光与光电子学进展，2021，58（16）：49-75.
WEN P，CHENG Y L，XU W S.Point cloud classification methods based on deep learning：a review[J].Laser & Optoelectronics Progress，2021，58（16）：49-75.
[4] 王文曦，李乐林.深度学习在点云分类中的研究综述[J].计算机工程与应用，2022，58（1）：26-40.
WANG W X，LI L L.Review of deep learning in point cloud classification[J].Computer Engineering and Applications，2022，58（1）：26-40.
[5] QI C R，SU H，MO K，et al.PointNet：deep learning on point sets for 3d classification and segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017.
[6] 白静，司庆龙，秦飞巍.轻量级实时点云分类网络LightPointNet[J].计算机辅助设计与图形学学报，2019，31（4）：612-620.
BAI J，SI Q L，QIN F W.Lightweight real-time point cloud classification network LightPointNet[J].Journal of Computer-Aided Design & Computer Graphics，2019，31（4）：612-620.
[7] 闫林，刘凯，段玫妤.一种用于点云分类的轻量级深度神经网络[J].西安电子科技大学学报，2020，47（2）：46-53.
YAN L，LIU K，DUAN M Y.Lightweight deep neural network for point cloud classification[J].Journal of Xidian University，2020，47（2）：46-53.
[8] QI C R，YI L，SU H，et al.Pointnet++：deep hierarchical feature learning on point sets in a metric space[C]//Advances in Neural Information Processing Systems，2017.
[9] WANG Y，SUN Y，LIU Z，et al.Dynamic graph CNN for learning on point clouds[J].ACM Transactions on Graphics，2018，38（5）：146.
[10] LI Y，BU R，SUN M，et al.PointCNN：convolution on Χ-transformed points[C]//Neural Information Processing Systems，2018.
[11] LECUN Y，BENGIO Y，HINTON G.Deep learning[J].Nature，2015，521（7553）：436-444.
[12] HUANG G，LIU Z，LAURENS V，et al.Densely connected convolutional networks[C]//IEEE Computer Society，2016.
[13] LAN S，YU R，YU G，et al.Modeling local geometric structure of 3D point clouds using Geo-CNN[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2019.
[14] LIN M，CHEN Q，YAN S.Network in network[C]//arXiv：1312.4400，2013.
[15] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[16] WU Z，SONG S，KHOSLA A，et al.3D ShapeNets：a deep representation for volumetric shapes[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2015.
[17] UY M A，PHAM Q H，HUA B S，et al.Revisiting point cloud classification：a new benchmark dataset and classification model on real-world data[C]//2019 IEEE/CVF International Conference on Computer Vision（ICCV），2020.
[18] YAN X，ZHENG C，LI Z，et al.PointASNL：robust point clouds processing using nonlocal neural networks with adaptive sampling[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：5589-5598.
[19] ZHANG K，HAO M，WANG J，et al.Linked dynamic graph CNN：learning on point cloud via linking hierarchical features[J].arXiv：1904.10014，2019.
[20] KOMARICHEV A，ZHONG Z，HUA J.A-CNN：annularly convolutional neural networks on point clouds[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020.
[21] ATZMON M，MARON H，LIPMAN Y.Point convolutional neural networks by extension operators[J].ACM Transactions on Graphics，2018，37（4CD）：1-12.
[22] QIU S，ANWAR S，BARNES N.Dense-resolution network for point cloud classification and segmentation[C]//Workshop on Applications of Computer Vision，2021.
[23] ZHAO H，JIANG L，FU C W，et al.Pointweb：enhancing local neighborhood features for point cloud processing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：5565-5573.
[24] BOULCH A.ConvPoint：continuous convolutions for point cloud processing[J].Computers & Graphics，2020，88：24-34.
[25] WU W，QI Z，LI F.PointConv：deep convolutional networks on 3D point clouds[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2019.
[26] XU Y，FAN T，XU M，et al.SpideRCNN：deep learning on point sets with parameterized convolutional filters[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：87-102.
[27] LIU Y，FAN B，XIANG S，et al.Relation-shape convolutional neural network for point cloud analysis[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：8895-8904.
[28] BROCK A，LIM T，RITCHIE J M，et al.Generative and discriminative voxel modeling with convolutional neural networks[J].arXiv：1608.04236v2，2016.