[1]李文举,姬倩倩,沙利业,等.基于图游走和图注意力的点云分类与分割[J].郑州大学学报(工学版),2024,45(02):33-41.[doi:10.13705/j.issn.1671-6833.2024.02.006]
 LI Wenju,JI Qianqian,SHA Liye,et al.Point Cloud Classification and Segmentation Based on Graph Walk and Graph Attention[J].Journal of Zhengzhou University (Engineering Science),2024,45(02):33-41.[doi:10.13705/j.issn.1671-6833.2024.02.006]
点击复制

基于图游走和图注意力的点云分类与分割()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
45卷
期数:
2024年02期
页码:
33-41
栏目:
出版日期:
2024-03-06

文章信息/Info

Title:
Point Cloud Classification and Segmentation Based on Graph Walk and Graph Attention
作者:
李文举1 姬倩倩1 沙利业2 储王慧1 崔 柳1
1. 上海应用技术大学 计算机科学与信息工程学院,上海 201418;2. 上海普利森配料系统有限公司,上海 201108
Author(s):
LI Wenju1 JI Qianqian1 SHA Liye2 CHU Wanghui1 CUI Liu1
1. School of Computer Science and Information Engineering, Shanghai Institute of Technology, Shanghai 201418, China; 2. Shanghai Precision Dosing & Weighing System Co. , Ltd. , Shanghai 201108, China
关键词:
点云分类 点云分割 图神经网络 图游走 图注意力机制
Keywords:
point cloud classification point cloud segmentation graph neural network graph walk graph attention mechanism
分类号:
TP391. 41;TP183
DOI:
10.13705/j.issn.1671-6833.2024.02.006
文献标志码:
A
摘要:
针对点云特征提取中远距离特征和局部几何结构信息欠缺的问题,提出了一种基于图游走和图注意力的 点云分类与分割网络。 首先,利用带有导向性的图游走算法,对点云全局特征补充额外的几何信息和远距离特征 信息;其次,嵌入图注意力机制,使模型聚焦于点云的关键区域,提升网络的特征提取能力;最后,在初始点云中提 取距离特征作为初始残差嵌入到网络中,避免网络过平滑。 在 ModelNet40 数据集、ScanObjectNN 数据集进行了点 云分类实验,在 ShapeNetPart 数据集与 Toronto-3D 数据集上分别进行了点云部件分割与点云语义分割实验,实验结 果表明:相较于基准网络 DGCNN,分类精度分别提升了 1. 3 百分点、5. 6 百分点;分割精度分别提升了 1. 2 百分点、 33. 1 百分点。 通过在 ModelNet40-C 数据集上进行稳健性分析,验证了所提网络具有较强的鲁棒性。
Abstract:
Aiming at the shortage of distance feature and local geometric structure information in feature extraction, a point cloud classification and segmentation network based on graph walk and graph attention was proposed. Firstly, a guided graph walk algorithm was used to supplement additional geometric information and remote feature information to the whole feature of point cloud. Secondly, the graph attention mechanism was embedded to make the model on the key areas of the point cloud and improve the feature extraction ability of the network. Finally, distance features were extracted from the initial point cloud and embedded into the network as initial residuals to avoid oversmoothing. Point cloud classification experiments were carried out on ModelNet40 dataset and ScanObjectNN dataset, and point cloud component segmentation and point cloud semantic segmentation experiments were carried out on ShapeNetPart dataset and Toronto-3D dataset, respectively. The experiment results showed that, compared with the benchmark network DGCNN, classification accuracy increased by 1. 3 percentages and 5. 6 percentages, respectively; The segmentation accuracy was improved by 1. 2 percentages and 33. 1 percentages respectively. Through the robust analysis on ModelNet40-C dataset, it was proved that the proposed network had strong robustness.

参考文献/References:

[1] 崔建明, 蔺繁荣, 张迪, 等. 基于有向图的强化学习 自动驾驶 轨 迹 预 测 [ J] . 郑 州 大 学 学 报 ( 工 学 版) , 2023, 44(5) : 53-61. 

CUI J M, LIN F R, ZHANG D, et al. Reinforcement learning autonomous driving trajectory prediction based on directed graph[ J] . Journal of Zhengzhou University (Engineering Science) , 2023, 44(5) : 53-61. 
[2] BELLO S A, YU S S, WANG C, et al. Review: deep learning on 3D point clouds[ J] . Remote Sensing, 2020, 12(11) : 1729.
 [3] 何雄辉, 谭杰夫, 刘哲, 等. 基于稀疏点云分割的适 应视角变化的场景识别方法[ J] . 计算机科学, 2023, 50(1) : 87-97.
 HE X H, TAN J F, LIU Z, et al. Viewpoint-tolerant scene recognition based on segmentation of sparse point cloud[ J] . Computer Science, 2023, 50(1) : 87-97. 
[4] GUO Y L, WANG H Y, HU Q Y, et al. Deep learning for 3D point clouds: a survey[ J] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43 (12) : 4338-4364. 
[5] 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. 
[6] QI C R, SU H, M K, 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. Piscataway: IEEE, 2017: 652 -660. 
[7] 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. New York: ACM, 2017: 5105-5114. 
[8] WANG Y, SUN Y B, LIU Z W, et al. Dynamic graph CNN for learning on point clouds[ J] . ACM Transactions on Graphics, 2019,38(5) : 1-12.
 [9] LI G H, MÜLLER M, THABET A, et al. DeepGCNs: can GCNs go as deep as CNNs? [ C]∥2019 IEEE / CVF International Conference on Computer Vision ( ICCV) . Piscataway:IEEE, 2019: 9266-9275. [
10] 逯泽锟, 于千城, 王晓峰, 等. 基于双重注意力机制 的符号网络节点嵌入[ J] . 郑州大学学报( 工学版) , 2023, 44(2) : 68-74. 
LU Z K, YU Q C, WANG X F, et al. Learning signed network node embedding via dual attention mechanism [ J] . Journal of Zhengzhou University ( Engineering Science) , 2023, 44(2) : 68-74. 
[11] WANG L, HUANG Y C, HOU Y L, et al. Graph attention convolution for point cloud semantic segmentation [C] ∥2019 IEEE / CVF Conference on Computer Vision and Pattern Recognition ( CVPR ) . Piscataway: IEEE, 2019: 10288-10297. 
[12] 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.
 [13] MA X, QIN C, YOU H X, et al. Rethinking network design and local geometry in point cloud: a simple residual MLP framework[EB / OL] . ( 2022 - 02 - 15) [ 2023 - 07 - 12] . https:∥arxiv. org / abs/ 2202. 07123. pdf. 
[14] CHEN M, WEI Z W, HUANG Z F, et al. Simple and deep graph convolutional networks [ C] ∥Proceedings of the 37th International Conference on Machine Learning. New York:ACM, 2020: 1725-1735. 
[15] XIANG T G, ZHANG C Y, SONG Y, et al. Walk in the cloud: learning curves for point clouds shape analysis[C]∥ 2021 IEEE / CVF International Conference on Computer Vision ( ICCV) . Piscataway:IEEE, 2021: 895-904. 
[16] WU Z R, SONG S R, KHOSLA A, et al. 3D ShapeNets: a deep representation for volumetric shapes [ C] ∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway:IEEE, 2015: 1912-1920.
 [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 ) . Piscataway:IEEE, 2019: 1588-1597. 
[18] YI L, KIM V G, CEYLAN D, et al. A scalable active framework for region annotation in 3D shape collections [ J ] . ACM Transactions on Graphics, 2016, 35 (6) : 1-12. 
[19] TAN W K, QIN N N, MA L F, et al. Toronto-3D: a large-scale mobile LiDAR dataset for semantic segmentation of urban roadways[C]∥2020 IEEE / CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway: IEEE, 2020: 797-806. 
[20] YAN X, ZHENG C D, LI Z, et al. PointASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling[C]∥2020 IEEE / CVF Conference on Computer Vision and Pattern Recognition ( CVPR) . Piscataway:IEEE, 2020: 5588-5597. 
[21] GOYAL A, LAW H, LIU B W, et al. Revisiting point cloud shape classification with a simple and effective baseline[EB / OL] . (2021-01-09) [ 2023-07-12] . https:∥arxiv. org / abs/ 2106. 05304. pdf. 
[22] LIN M X, FERAGEN A. DiffConv: analyzing irregular point clouds with an irregular view[C]∥European Conference on Computer Vision. Cham: Springer, 2022: 380 -397.
 [23] 兰红, 陈浩, 张蒲芬. 集图卷积和三维方向卷积的点 云分类分割模型[ J] . 计算机工程与应用, 2023, 59 (8) : 182-191. 
LAN H, CHEN H, ZHANG P F. Point cloud classification and segmentation model based on graph convolution and 3D direction convolution[ J] . Computer Engineering and Applications, 2023, 59(8) : 182-191. 
[24] 沈露, 杨家志, 周国清, 等. 集自注意力与边卷积的 点云分类分割模型[ J] . 计算机工程与应用, 2023, 59 (19) : 106-113. 
SHEN L, YANG J Z, ZHOU G Q, et al. Point cloud classification segmentation model based on self-attention and edge convolution[ J] . Computer Engineering and Applications, 2023, 59(19) : 106-113. 
[25] GUO M H, CAI J X, LIU Z N, et al. PCT: point cloud transformer[ J ] . Computational Visual Media, 2021, 7 (2) : 187-199.
 [26] SUN J C, ZHANG Q Z, KAILKHURA B, et al. Benchmarking robustness of 3D point cloud recognition against common corruptions[ EB / OL] . ( 2022 - 01 - 28) [ 2023 - 07-12] . https:∥arxiv. org / abs/ 2201. 12296. pdf.

更新日期/Last Update: 2024-03-08