结合分割算法和图卷积网络的车载点云分类方法

doi:10.3969/j.issn.0255-8297.2024.03.003

摘要/Abstract

摘要： 车载点云数据语义标注是道路场景语义分析和理解的前提，该文提出了结合分割算法和图卷积网络的车载点云分类方法。首先利用具有噪声的基于密度的聚类方法（densitybased spatial clustering of applications with noise,DBSCAN）将点云分割成点簇，并以点簇为节点，相邻点簇构成边，节点和边形成图；然后利用图卷积网络对图节点进行半监督分类，得到点云中任一点的类别标注。实验表明，所提方法以点簇代替原始点云，极大减少了算法处理的数据量；半监督图卷积网络模型顾及了点云数据的上下文关联，在少量标注样本的情况下，能够获得较高的分类精度，场景简单的实验数据分类精度可以与Pointnet++模型相当，场景较为复杂的实验数据分类精度与Pointnet++模型相差在6.7%以内。

关键词: 点云分割, 图卷积网络, 点云分类

Abstract: Vehicle-mounted LiDAR point cloud semantic annotation is a prerequisite for further semantic analysis and understanding of road scenes. This paper proposes a point cloud classification method that integrates segmentation algorithm and graph convolution network. First, point cloud is segmented into point clusters using the density-based spatial clustering of applications with noise (DBSCAN) algorithm. Point clusters are treated as nodes, with adjacent clusters forming edges, thus constituting a graph. Then, graph convolution network is used to semi-supervise the classification of graph nodes and obtain the semantic annotation of any point in the point cloud. Experimental results demonstrate that replacing the original point cloud with point clusters greatly reduces the amount of data processed by the algorithm. Furthermore, the semi-supervised graph convolution network, considering the context of point cloud, achieves high classification accuracy even with a small number of labeled samples. The classification accuracy of experimental data with simple scenes is comparable to that of pointnet++, with the difference in accuracy below 6.7% for complex scenes.

Key words: point cloud segmentation, graph convolution network, point cloud classification

中图分类号:

P208

刘亚文, 刘永畅. 结合分割算法和图卷积网络的车载点云分类方法[J]. 应用科学学报, 2024, 42(3): 405-415.

LIU Yawen, LIU Yongchang. Vehicle-Mounted LiDAR Point Cloud Data Classification Based on Segmentation Algorithm and Graph Convolution Network[J]. Journal of Applied Sciences, 2024, 42(3): 405-415.

参考文献

[1] Su H, Maji S, Kalogerakis E, et al. Multi-view convolutional neural networks for 3D shape recognition [C]//IEEE International Conference on Computer Vision (ICCV), 2015: 945-953.
[2] Boulch A, Guerry J, Le S B, et al. SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks [J]. Computers & Graphics, 2018, 71(4): 189-198.
[3] Maturana D, Scherer S. VoxNet: a 3D convolutional neural network for real-time object recognition [C]//IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015: 922-928.
[4] Wu Z R, Song S R, Khosla A, et al. 3D ShapeNets: a deep representation for volumetric shapes [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 1912-1920.
[5] Riegler G, Ulusoy A O, Geiger A. OctNet: learning deep 3D representations at high resolutions [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 3577-3586.
[6] Tchapmi L, Choy C, Armeni I, et al. SEGCloud: semantic segmentation of 3D point clouds [C]//2017 International Conference on 3D Vision (3DV), 2017: 537-547.
[7] Charles R Q, Hao S, Mo K C, et al. PointNet: deep learning on point sets for 3D classification and segmentation [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 77-85.
[8] Qi C R, Yi L, Su H, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space [C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 5099-5108.
[9] Landrieu L, Simonovsky M. Large-scale point cloud semantic segmentation with superpoint graphs [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 4558-4567.
[10] Hua B S, Tran M K, Yeung S K. Pointwise convolutional neural networks [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 984-993.
[11] 项彬彬. 基于深度学习的车载道路场景点云自动分类[D]. 武汉: 武汉大学, 2019.
[12] 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): 1600003. Wen P, Cheng Y L, Yu W S. Point cloud classification methods based on deep learning: a review [J]. Laser & Optoelectronics Progress, 2021, 58(16): 1600003. (in Chinese)
[13] 陈苏婷, 陈怀新, 张闯. 基于图卷积神经网络的三维点云分割算法Graph-PointNet [J]. 现代电子技术, 2022, 45(6): 87-92. Chen S T, Chen H X, Zhang C. 3D point cloud segmentation algorithm Graph-PointNet based on GCNN [J]. Modern Electronics Technique, 2022, 45(6): 87-92. (in Chinese)
[14] Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering [C]//Proceedings of the 30th International Conference on Neural Information Processing Systems, 2016: 3844-3852.
[15] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks [C]//International Conference on Learning Representations (ICLR), 2017: 99.
[16] Scarselli F, Gori M, Tsoi A C, et al. The graph neural network model [J]. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80.
[17] Hamilton W L, Ying R, Leskovec J. Inductive representation learning on large graph [C]//The 31st International Conference on Neural Information Processing Systems, 2017: 1025-1035.
[18] 徐冰冰, 岑科廷, 黄俊杰, 等. 图卷积神经网络综述[J]. 计算机学报, 2020, 43(5): 755-780. Xu B B, Cen K T, Huang J J, et al. A survey on graph convolutional neural network [J]. Chinese Journal of Computers, 2020, 43(5): 755-780. (in Chinese)
[19] 屠恩美, 杨杰. 半监督学习理论及其研究进展概述[J]. 上海交通大学学报, 2018, 52(10): 1280-1291. Tu E M, Yang J. A review of semi-supervised learning theories and recent advances [J]. Journal of Shanghai Jiao Tong University, 2018, 52(10): 1280-1291. (in Chinese)
[20] 刘亚文, 张颖. 结合上下文特征和图割算法的车载点云聚类方法[J]. 应用科学学报, 2020, 38(6): 924-935. Liu Y W, Zhang Y. Vehicle point cloud clustering based on contextual feature and graph cut [J]. Journal of Applied Sciences, 2020, 38(6): 924-935. (in Chinese)
[21] Demantké J, Mallet C, David N, et al. Dimensionality based scale selection in 3D LiDAR point clouds [J]. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012: 97-102.
[22] West K F, Webb B N, Lersch J R, et al. Context-driven automated target detection in 3D data [C]//The 14th Conference on Automatic Target Recognition, 2004: 133-143.
[23] Guinard S, Landrieu L. Weakly supervised segmentation-aided classification of urban scenes from 3D LiDAR point clouds [J]. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, 151-157.