基于图卷积神经网络的点云语义分割综述

doi:10.11896/jsjkx.230400196

摘要/Abstract

摘要： 随着点云在自动驾驶、地图测绘和矿山测量等领域的广泛应用,人们愈发关注这种蕴含丰富信息的数据表示形式。点云语义分割作为点云数据处理的重要手段,因具有极高的研究价值和应用前景而受到广泛关注。由于点云所具有的置换不变性和旋转不变性等特点,传统的卷积神经网络无法直接处理不规则的点云数据,而图卷积神经网络却可以使用图卷积算子直接提取点云特征,逐步成为当前点云分割领域的研究热点。虽已有综述性文章对点云分割方法做出总结,但这些文章对图卷积的介绍较为粗略。因而对近几年基于图卷积的点云分割方法进行了分析和归类,总结每类方法的研究思路和特点;然后,介绍了一些在点云语义分割领域中主流的点云数据集和评价指标,并对提及的分割方法的实验结果进行对比;最后,对各类方法的发展方向进行了展望。

关键词: 语义分割, 点云, 图卷积神经网络, 深度学习, 计算机视觉

Abstract: As point clouds are widely utilized in various fields such as autonomous driving,map making,and mining measurement,there is a growing interest in this data representation that contains rich information.Point cloud semantic segmentation,as an important means of point cloud data processing,has attracted wide attention due to its high research value and application prospects.Due to the characteristics of permutation invariance and rotation invariance in point clouds,traditional convolutional neural networks cannot directly process irregular point cloud data,but graph convolutional neural networks can use graph convolution operators to directly extract point cloud features.Therefore,this paper provides a detailed review of recent point cloud segmentation methods based on graph convolution.The methods are further divided according to the type of graph convolution,and representative algorithms in each category are introduced and analyzed,summarizing the research ideas and advantages and disadvantages of each method.Then,some mainstream point cloud datasets and evaluation metrics in the field of point cloud semantic segmentation are introduced,and the experimental results of the mentioned segmentation methods are compared.Finally,the development direction of various methods is discussed.

Key words: Semantic segmentation, Point clouds, Graph convolution neural network, Deep learning, Computer vision

中图分类号:

TP391

黄海新, 蔡明启, 王钰瑶. 基于图卷积神经网络的点云语义分割综述[J]. 计算机科学, 2024, 51(6A): 230400196-7. https://doi.org/10.11896/jsjkx.230400196

HUANG Haixin, CAI Mingqi, WANG Yuyao. Review of Point Cloud Semantic Segmentation Based on Graph Convolutional Neural Networks[J]. Computer Science, 2024, 51(6A): 230400196-7. https://doi.org/10.11896/jsjkx.230400196

参考文献

[1]QI C R,SU H,MOK,et al.Pointnet:Deep learning on point sets for 3d classification and segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:652-660.
[2]QI C R,YI L,SUH P N,et al.Deep hierarchical feature learning on point sets in a metric space.arXiv 2017[J].arXiv:1706.02413,2017.
[3]HUANG Q,WANG W,NEUMANN U.Recurrent slice net-works for 3d segmentation of point clouds[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:2626-2635.
[4]ZHANG S,TONG H,XU J,et al.Graph convolutional net-works:a comprehensive review[J].Computational Social Networks,2019,6(1):1-23.
[5]BRUNA J,ZAREMBA W,SZLAM A,et al.Spectral networks and locally connected networks on graphs[J].arXiv:1312.6203,2013.
[6]WANG C,SAMARI B,SIDDIQI K.Local spectral graph convolution for point set feature learning[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:52-66.
[7]TE G,HU W,ZHENG A,et al.Rgcnn:Regularized graph cnnfor point cloud segmentation[C]//Proceedings of the 26th ACM international conference on Multimedia.2018:746-754.
[8]LU Q,CHEN C,XIE W,et al.PointNGCNN:Deep convolutionalnetworks on 3D point clouds with neighborhood graph filters[J].Computers & Graphics,2020,86:42-51.
[9]LI W,MA Q,TIAN W,et al.Graph Convolution Network with Double Filter for Point Cloud Segmentation[C]//2020 5th International Conference on Intelligent Informatics and Biomedical Sciences(ICIIBMS).IEEE,2020:168-173.
[10]WANG Y,SUN Y,LIU Z,et al.Dynamic graph cnn for learning on point clouds[J].ACM Transactions On Graphics(tog),2019,38(5):1-12.
[11]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.
[12]CHEN L,ZHANG Q.Ddgcn:graph convolution network based on direction and distance for point cloud learning[J].The Visual Computer,2023,39(3):863-873.
[13]WANG Y,XIAO S.Affinity-Point Graph Convolutional Net-work for 3D Point Cloud Analysis[J].Applied Sciences,2022,12(11):5328.
[14]CHEN C,FRAGONARA L Z,TSOURDOS A.GAPointNet:Graph attention based point neural network for exploiting local feature of point cloud[J].Neurocomputing,2021,438:122-132.
[15]WANG L,HUANG Y,HOU Y,et al.Graph attention convolution for point cloud semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:10296-10305.
[16]JING W,ZHANG W,LI L,et al.AGNet:An attention-based graph network for point cloud classification and segmentation[J].Remote Sensing,2022,14(4):1036.
[17]ZHAI R,ZOU J,HE Y,et al.IAGC:interactive attention graph convolution network for semantic segmentation of point clouds in building indoor environment[J].ISPRS International Journal of Geo-Information,2022,11(3):181.
[18]DENG C,PENG Z,CHEN Z,et al.Point Cloud Deep Learning Network Based on Balanced Sampling and Hybrid Pooling[J].Sensors,2023,23(2):981.
[19]LI G,MULLER M,THABET A,et al.Deepgcns:Can gcns go as deep as cnns?[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:9267-9276.
[20]LI G,XIONG C,THABET A,et al.Deepergcn:All you need to train deeper gcns[J].arXiv:2006.07739,2020.
[21]WANG X,JIANG B,ZHANG Z,et al.DeepGCNs-Att for Point Cloud Semantic Segmentation[C]//Journal of Physics:Confe-rence Series.IOP Publishing,2021:012059.
[22]HE Q,BANERJEE S,SCHWIEBERT L,et al.AgileGCN:Accelerating Deep GCN with Residual Connections using Structured Pruning[C]//2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval(MIPR).IEEE,2022:20-26.
[23]ENGELMANN F,KONTOGIANNI T,LEIBE B.Dilated pointconvolutions:On the receptive field size of point convolutions on 3d point clouds[C]//2020 IEEE International Conference on Robotics and Automation(ICRA).IEEE,2020:9463-9469.
[24]WAN J,XIE Z,XU Y,et al.DGANet:A dilated graph attention-based network for local feature extraction on 3D point clouds[J].Remote Sensing,2021,13(17):3484.
[25]WANG L,WU J,LIU X,et al.Semantic segmentation of large-scale point clouds based on dilated nearest neighbors graph[J].Complex & Intelligent Systems,2022,8(5):3833-3845.
[26]MAO Y,SUN X,DIAO W,et al.Semantic segmentation forpoint cloud scenes via dilated graph feature aggregation and pyramid decoders[J].arXiv:2204.04944,2022.
[27]LANDRIEU L,SIMONOVSKY M.Large-scale point cloud semantic segmentation with superpoint graphs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:4558-4567.
[28]GENG Y,WANG Z,JIA L,et al.3DGraphSeg:A unified graph representation-based point cloud segmentation framework for full-range highspeed railway environments[J].IEEE Transactions on Industrial Informatics,2023,19(2):11430-11443.
[29]LI Y,MA L,ZHONG Z,et al.TGNet:Geometric graph CNN on 3-D point cloud segmentation[J].IEEE Transactions on Geo-science and Remote Sensing,2019,58(5):3588-3600.
[30]WEI M,WEI Z,ZHOU H,et al.AGConv:Adaptive Graph Convolution on 3D Point Clouds[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2023,45(8):9374-9392.
[31]YANG F,DAVOINE F,WANG H,et al.Continuous conditional random field convolution for point cloud segmentation[J].Pattern Recognition,2022,122:108357.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed