基于局部-非局部交互卷积的3D点云分类

doi:10.16451/j.cnki.issn1003-6059.202202005

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (962 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要现阶段点云分类研究已被广泛应用于机器人操作、自主驾驶和虚拟现实等多个领域,提取既丰富又具有高判别能力的特征是3D点云分类的关键.为此,文中设计基于局部-非局部交互卷积的3D点云分类算法,改善点云的特征提取.首先,构造局部-非局部交互卷积模块,在获取局部相似特征和非局部相似特征的基础上,采用交互增强,缓解单个邻域在表示封闭区域时存在的冗余问题,增强网络的层次性和稳定性,同时也缓解网络的退化问题.然后,以该模块为基本单元构建卷积神经网络.最后,采用自适应特征融合,充分利用不同层次的特征,实现3D点云的分类.在ModelNet40、ScanObjectNN基准数据集上的实验表明,文中算法性能较优.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	芦新宇
	杨冰
	叶海良
	曹飞龙

关键词 ：深度学习, 点云分类, 局部-非局部交互卷积, 自适应特征融合

Abstract：Now 3D point cloud classificaiton is widely applied in many domains, including robot operation, automous driving and virtual reality. Extracting rich features with high discrimination is the key to 3D point cloud classification. Therefore, an algorithm of 3D point cloud classification based on local-nonlocal interactive convolution is designed to improve the feature extraction of point cloud. Firstly, a local-nonlocal interactive convolution module is constructed. After obtaining local and nonlocal similar features, interactive enhancement is employed to alleviate the redundancy problem caused by a single neighborhood representing a closed region. Consequently, the hierarchy and stability of the network are enhanced and the degradation problem of the network is alleviated. Then, the convolution neural network is constructed with the module as the basic unit. Finally, adaptive feature fusion is adopted to make full use of different levels of features to realize 3D point cloud classification. Experimental results on two benchmark datasets, ModelNet40 and ScanObjectNN, show that the proposed method generates better performance.

Key words： Deep Learning Point Cloud Classification Local-Nonlocal Interactive Convolution Adaptive Feature Fusion

收稿日期: 2021-10-25

ZTFLH:

TP 391

基金资助:国家自然科学基金项目(No.62032022,62006215)资助

通讯作者: 曹飞龙,博士,教授,主要研究方向为深度学习、图像处理等.E-mail:feilongcao@gmail.com.

作者简介: 芦新宇,硕士研究生,主要研究方向为深度学习、点云分析等.E-mail:wylxy328@163.com.杨冰,博士,讲师,主要研究方向为深度学习、图像处理.E-mail:bingyang0517@163.com.叶海良,博士,讲师,主要研究方向为深度学习、图像处理.E-mail:yhl575@163.com.

引用本文:

芦新宇, 杨冰, 叶海良, 曹飞龙. 基于局部-非局部交互卷积的3D点云分类[J]. 模式识别与人工智能, 2022, 35(2): 141-149. LU Xinyu, YANG Bing, YE Hailiang, CAO Feilong. 3D Point Cloud Classification Based on Local-Nonlocal Interactive Convolution. Pattern Recognition and Artificial Intelligence, 2022, 35(2): 141-149.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202202005 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2022/V35/I2/141

[1] RUSU R B, MARTON Z C, BLODOW N, et al. Towards 3D Point Cloud Based Object Maps for Household Environments. Robotics and Autonomous Systems, 2008, 56(11): 927-941.
[2] QI C R, LIU W, WU C X, et al. Frustum PointNets for 3D Object Detection from RGB-D Data//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 918-927.
[3] RAHMAN M M, TAN Y H, XUE J, et al. Recent Advances in 3D Object Detection in the Era of Deep Neural Networks: A Survey. IEEE Transactions on Image Processing, 2020, 29: 2947-2962.
[4] QI C R, SU H, MO K C, et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 652-660.
[5] QI C R, YI L, SU H, et al.PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space//Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2017: 5105-5114.
[6] 陆军,华博文,朱波.基于局部曲面特征直方图的点云识别.模式识别与人工智能, 2020, 33(10): 934-943.
(LU J, HUA B W, ZHU B.Point Cloud Recognition Based on Local Surface Feature Histogram. Pattern Recognition and Artificial Intelligence, 2020, 33(10): 934-943.)
[7] WU H, MIAO Y B, FU R C.Point Cloud Completion Using Multiscale Feature Fusion and Cross-Regional Attention. Image and Vision Computing, 2021, 111. DOI: 10.1016/j.imavis.2021.104193.
[8] MATURANA D, SCHERER S.VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition//Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Wa-shington, USA: IEEE, 2015: 922-928.
[9] SU H, MAJI S, KALOGERAKIS E, et al. Multi-view Convolutional Neural Networks for 3D Shape Recognition//Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 945-953.
[10] 侯向丹,于习欣,刘洪普.基于图卷积网络的三维点云分类分割模型.激光与光电子学进展, 2020, 57(18): 204-211.
(HOU X D, YU X X, LIU H P.3D Point Cloud Classification and Segmentation Model Based on Graph Convolutional Network. Laser & Optoelectronics Progress, 2020, 57(18): 204-211.)
[11] XU Y F, FAN T Q, XU M Y, et al. SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters//Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 90-105.
[12] LI Y Y, BU R, SUN M C, et al.PointCNN: Convolution on χ-Transformed Points//Proc of the 32nd Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2018: 820-830.
[13] SIMONOVSKY M, KOMODAKIS N.Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 3693-3702.
[14] WANG Y, SUN Y B, LIU Z W, et al. Dynamic Graph CNN for Learning on Point Clouds. ACM Transactions on Graphics, 2019, 38(5): 1-12.
[15] 梁振明,翟正利,周炜.基于多尺度动态图卷积网络的3D点云分类.计算机应用与软件, 2021, 38(5): 263-267, 306.
(LIANG Z M, ZHAI Z L, ZHOU W.3D Point Clouds Classification Based on Multi-scale Dynamic Graph Convolutional Network. Computer Applications and Software, 2021, 38(5): 263-267, 306.)
[16] 杜子金,曹飞龙,叶海良,等.基于残差边卷积的3D点云分类算法.模式识别与人工智能, 2021, 34(9): 836-843.
(DU Z J, CAO F L, YE H L, et al. 3D Point Cloud Classification Algorithm Based on Residual Edge Convolution. Pattern Recognition and Artificial Intelligence, 2021, 34(9): 836-843. )
[17] XU M Y, ZHOU Z P, QIAO Y.Geometry Sharing Network for 3D Point Cloud Classification and Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 37(7): 12500-12507.
[18] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778.
[19] WU Z R, SONG S R, KHOSLA A, et al. 3D ShapeNets: A Deep Representation for Volumetric Shapes//Proc of the IEEE Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 1912-1920.
[20] 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//Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 1588-1597.
[21] LI J X, CHEN B M, LEE G H.SO-Net: Self-Organizing Network for Point Cloud Analysis//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 9397-9406.
[22] KLOKOV R, LEMPITSKY V.Escape from Cells: Deep KD-Networks for the Recognition of 3D Point Cloud Models//Proc of the IEEE International Conference on Computer Vision. Washington USA: IEEE, 2017: 863-872.
[23] BOULCH A.ConvPoint: Continuous Convolutions for Point Cloud Processing. Computers and Graphics, 2020, 88: 24-34.
[24] ATZMON M, MARON H, LIPMAN Y.Point Convolutional Neural Networks by Extension Operators. ACM Transactions on Graphics, 2018, 37(4): 1-12.
[25] WU W X, QI Z G, LI F X.PointConv: Deep Convolutional Networks on 3D Point Clouds//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 9621-9630.
[26] KOMARICHEV A, ZHONG Z C, HUA J.A-CNN: Annularly Convolutional Neural Networks on Point Clouds//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 7413-7422.
[27] LIU Y C, FAN B, XIANG S M, et al. Relation-Shape Convolutional Neural Network for Point Cloud Analysis//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 8887-8896.
[28] CHEN C, FRAGONARA L Z, TSOURDOS A.GAPointNet: Graph Attention Based Point Neural Network for Exploiting Local Feature of Point Cloud. Neurocomputing, 2021, 438: 122-132.
[29] QIU S, ANWAR S, BARNES N.Dense-Resolution Network for Point Cloud Classification and Segmentation//Proc of the IEEE Winter Conference on Applications of Computer Vision. Washington, USA: IEEE, 2021: 3813-3822.
[30] YAN X, ZHENG C D, LI Z, et al. PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks with Adaptive Sampling//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 5588-5597.
[31] LAN S Y, YU R C, YU G, et al. Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 998-1008.
[32] BEN-SHABAT Y, LINDENBAUM M, FISCHER A.3D Point Cloud Classification and Segmentation Using 3D Modified Fisher Vector Representation for Convolutional Neural Networks [C/OL]. [2021-10-12].https://arxiv.org/pdf/1711.08241.pdf.
[33] RAO Y M, LU J W, ZHOU J.Global-Local Bidirectional Reaso-ning for Unsupervised Representation Learning of 3D Point Clouds//Proc of the IEEE/CVF Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2020: 5375-5385.
[34] VAN DER MAATEN L, HINTON G. Visualizing Data Using t-SNE. Journal of Machine Learning Research, 2008, 9: 2579-2605.