Point cloud classification and segmentation method based on adaptive dynamic graph convolution and parameter-free attention

doi:10.11772/j.issn.1001-9081.2024060878

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (6): 1980-1986.DOI: 10.11772/j.issn.1001-9081.2024060878

• Multimedia computing and computer simulation • Previous Articles

Point cloud classification and segmentation method based on adaptive dynamic graph convolution and parameter-free attention

Weigang LI¹^,², Xinyi LI¹(), Yongqiang WANG¹, Yuntao ZHAO¹

^1.School of Information Science and Engineering，Wuhan University of Science and Technology，Wuhan Hubei 430081，China
^2.Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education （Wuhan University of Science and Technology），Wuhan Hubei 430081，China

Received:2024-06-27 Revised:2024-08-30 Accepted:2024-09-06 Online:2024-10-29 Published:2025-06-10
Contact: Xinyi LI
About author:LI Weigang， born in 1977， Ph. D.， professor. His research interests include industrial process control， artificial intelligence， machine learning algorithms.
LI Xinyi， born in 2000， M. S. candidate. Her research interests include point cloud data processing， deep learning， pattern recognition.
WANG Yongqiang， born in 1994， Ph. D. candidate. His research interests include intelligent processing of point cloud.
ZHAO Yuntao， born in 1982， Ph. D.， professor. His research interests include robot dynamics， 3D machine vision.
Supported by:
Hubei Provincial Science and Technology Talent Service Enterprise Project(202400288)

基于自适应动态图卷积和无参注意力的点云分类分割方法

李维刚¹^,², 李歆怡¹(), 王永强¹, 赵云涛¹

^1.武汉科技大学信息科学与工程学院，武汉 430081
^2.冶金自动化与检测技术教育部工程研究中心（武汉科技大学），武汉 430081

通讯作者: 李歆怡
作者简介:李维刚（1977—），男，湖北咸宁人，教授，博士，主要研究方向：工业过程控制、人工智能、机器学习算法
李歆怡（2000 —），女，湖北武汉人，硕士研究生，主要研究方向：点云数据处理、深度学习、模式识别 lixinyi_myself@163.com
王永强（1994—），男，河南许昌人，博士研究生，主要研究方向：点云智能处理
赵云涛（1982—），男，内蒙古赤峰人，教授，博士，主要研究方向：机器人动力学、三维机器视觉。
基金资助:
湖北省科技人才服务企业项目(202400288)

Abstract

Abstract:

To address the challenges of traditional convolution in extracting neighborhood feature information accurately and integrating contextual information effectively in point cloud processing， a point cloud classification and segmentation method based on adaptive dynamic graph convolution and parameter-free attention was proposed. Firstly， the Adaptive Dynamic Graph Convolution module （ADGC） was used to learn feature information of different neighborhoods， generate the adaptive convolution kernels， and update the edge features， thereby extracting local neighborhood features of the point cloud accurately. Then， a residual structure was designed to learn spatial position information of the point cloud， so as to capture geometric structure between the point pairs accurately， and better retain and extract the detailed features. Finally， in order to better pay attention to and extract the local geometric features， the Parameter-Free Attention module （PFA） was combined with convolution operation to enhance connection among the neighbors and improve context-aware ability of the model. Experimental results show that compared to PointNet， the proposed method has significant advantages across various tasks. In specific， the proposed method has an increase of 4.6 percentage points in Overall Accuracy （OA） for classification tasks， an increase of 2.3 percentage points in mean Intersection over Union （mIoU） for part segmentation tasks， and an increase of 24.6 percentage points in mIoU for semantic segmentation tasks. It can be seen that the proposed method further improves the understanding and representation abilities of complex geometries， resulting in more accurate feature extraction and experimental performance in a variety of tasks.

Key words: point cloud, classification and segmentation, adaptive, dynamic graph convolution, attention mechanism

摘要：

针对传统卷积在处理点云时难以精确提取邻域特征信息和有效融合上下文信息的问题，提出一种基于自适应动态图卷积和无参注意力的点云分类分割方法。首先，通过自适应动态图卷积模块（ADGC）学习不同邻域的特征信息，生成自适应卷积核，并更新边缘特征，从而精确提取点云的局部邻域特征；其次，设计残差结构学习点云的空间位置信息，以精确捕获点对之间的几何结构，更好地保留和提取细节特征；最后，为了更好地关注和提取局部几何特征，结合无参注意力模块（PFA）与卷积操作，增强邻域之间的联系和模型的上下文感知能力。实验结果表明，与PointNet相比，所提方法在多种任务上具有显著优势，具体地，所提方法的分类任务的总体精度（OA）提升了4.6个百分点，部件分割任务实例的平均交并比（mIoU）提升了2.3个百分点，语义分割任务的mIoU提升了24.6个百分点。可见，所提方法进一步增强了对复杂几何结构的理解和表征能力，在各种任务中实现了更精确的特征提取和实验性能。

关键词: 点云, 分类分割, 自适应, 动态图卷积, 注意力机制

CLC Number:

TP391.4

Weigang LI, Xinyi LI, Yongqiang WANG, Yuntao ZHAO. Point cloud classification and segmentation method based on adaptive dynamic graph convolution and parameter-free attention[J]. Journal of Computer Applications, 2025, 45(6): 1980-1986.

李维刚, 李歆怡, 王永强, 赵云涛. 基于自适应动态图卷积和无参注意力的点云分类分割方法[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1980-1986.

Figures/Tables 13

References 29

1	FENG W， LI J， CAI H， et al. Neural points： point cloud representation with neural fields for arbitrary upsampling［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 18612-18621.
2	JIANG L， ZHANG J， DENG B. Robust RGB-D face recognition using attribute-aware loss［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2020， 42（10）： 2552-2566.
3	LI Y， IBANEZ-GUZMAN J. Lidar for autonomous driving： the principles， challenges， and trends for automotive lidar and perception systems［J］. IEEE Signal Processing Magazine， 2020， 37（4）： 50-61.
4	XIONG J， HSIANG E L， HE Z， et al. Augmented reality and virtual reality displays： emerging technologies and future perspectives［J］. Light： Science and Applications， 2021， 10： No.216.
5	WANG J， CHEN J， SUN Y， et al. RobOT： robustness-oriented testing for deep learning systems［C］// Proceedings of the IEEE/ACM 43rd International Conference on Software Engineering. Piscataway： IEEE， 2021： 300-311.
6	MIRZAEI K， ARASHPOUR M， ASADI E， et al. 3D point cloud data processing with machine learning for construction and infrastructure applications： a comprehensive review［J］. Advanced Engineering Informatics， 2022， 51： No.101501.
7	WU Z， SONG S， KHOSLA A， et al. 3D ShapeNets： a deep representation for volumetric shapes ［C］// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2015： 1912-1920.
8	SU H， MAJI S， KALOGERAKIS E， et al. Multi-view convolutional neural networks for 3D shape recognition［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2015： 945-953.
9	QI C R， SU H， MO K， et al. PointNet： deep learning on point sets for 3D classification and segmentation ［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 77-85.
10	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. Red Hook： Curran Associates Inc.， 2017： 5105-5114.
11	WANG Y， SUN Y， LIU Z， et al. Dynamic graph CNN for learning on point clouds［J］. ACM Transactions on Graphics， 2019， 38（5）： No.146.
12	ZHANG K， HAO M， WANG J， et al. Linked dynamic graph CNN： Learning on point cloud via linking hierarchical features［C］// Proceedings of the 27th International Conference on Mechatronics and Machine Vision in Practice. Piscataway： IEEE， 2021： 7-12.
13	WANG L， HUANG Y， HOU Y， et al. Graph attention convolution for point cloud semantic segmentation［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 10288-10297.
14	LIN Z H， HUANG S Y， WANG Y C F. Learning of 3D graph convolution networks for point cloud analysis［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2022， 44（8）： 4212-4224.
15	李维刚，陈婷，田志强. 基于孪生自适应图卷积算法的点云分类与分割［J］. 计算机应用， 2023， 43（11）： 3396-3402.
	LI W G， CHEN T， TIAN Z Q. Point cloud classification and segmentation based on Siamese adaptive graph convolution algorithm ［J］. Journal of Computer Applications， 2023， 43（11）： 3396-3402.
16	刘斌，樊云超. 基于改进动态图卷积的点云分类模型［J］. 中国科技论文， 2022， 17（11）： 1230-1235， 1266.
	LIU B， FAN Y C. A point cloud classification model based on improved dynamic graph convolution ［J］. China Sciencepaper， 2022， 17（11）： 1230-1235， 1266.
17	任欢，王旭光. 注意力机制综述［J］. 计算机应用， 2021， 41（S1）： 1-6.
	REN H， WANG X G. Review of attention mechanism［J］. Journal of Computer Applications， 2021， 41（S1）： 1-6.
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 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 5588-5597.
19	GUO M H， CAI J X， LIU Z N， et al. PCT： point cloud Transformer［J］. Computational Visual Media， 2021， 7（2）： 187-199.
20	LU D， GAO K， XIE Q， et al. 3DPCT： 3D point cloud transformer with dual self-attention ［EB/OL］. ［2024-08-25］..
21	GAO J， LAN J， WANG B， et al. SDANet： spatial deep attention-based for point cloud classification and segmentation ［J］. Machine Learning， 2022， 111（4）： 1327-1348.
22	WU C， ZHENG J， PFROMMER J， et al. Attention-based point cloud edge sampling［C］// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2023： 5333-5343.
23	JIANG J， ZHAO L， LU X， et al. DHGCN： dynamic hop graph convolution network for self-supervised point cloud learning ［C］// Proceedings of the 38th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2024： 12883-12891.
24	MA X， QIN C， YOU H， et al. Rethinking network design and local geometry in point cloud： a simple residual MLP framework［EB/OL］. ［2024-08-25］..
25	HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 7132-7141.
26	YANG L， ZHANG R Y， LI L， et al. SimAM： a simple， parameter-free attention module for convolutional neural networks［C］// Proceedings of the 38th International Conference on Machine Learning. New York： JMLR.org， 2021： 11863-11874.
27	LI Y， BU R， SUN M， et al. PointCNN： convolution on X -transformed points［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2018： 828-838.
28	YI L， KIM V G， CEYLAN D， et al. A scalable active framework for region annotation in 3D shape collections［J］. ACM Transaction on Graphics， 2016， 35（6）： No.210.
29	ARMENI I， SENER O， ZAMIR A R， et al. 3D semantic parsing of large-scale indoor spaces［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 1534-1543.

方法	输入	mAcc	OA
MVCNN	View	—	90.1
3D ShapeNets	Voxels	77.5	84.5
PointNet	xyz	86.2	89.2
PointNet++	xyz+normal	—	91.9
PointCNN	xyz	—	92.2
DGCNN	xyz	89.8	92.6
3D-GCN	xyz	—	92.1
PointASNL	xyz+normal	—	93.2
PCT	xyz	—	93.2
APES（local-based）	xyz	—	93.5
APES（global-based）	xyz	—	93.8
DHGCN	xyz	—	93.0
本文方法	xyz	91.2	93.8

方法	输入	mAcc	OA
MVCNN	View	—	90.1
3D ShapeNets	Voxels	77.5	84.5
PointNet	xyz	86.2	89.2
PointNet++	xyz+normal	—	91.9
PointCNN	xyz	—	92.2
DGCNN	xyz	89.8	92.6
3D-GCN	xyz	—	92.1
PointASNL	xyz+normal	—	93.2
PCT	xyz	—	93.2
APES（local-based）	xyz	—	93.5
APES（global-based）	xyz	—	93.8
DHGCN	xyz	—	93.0
本文方法	xyz	91.2	93.8

方法	mean	mIoU/%
方法	mean	飞机	包	帽子	汽车	椅子	耳机	吉他	刀	灯	电脑	摩托	水杯	手枪	火箭	滑板	桌子
PointNet	83.7	83.4	78.7	82.5	74.9	89.6	73.0	91.5	85.9	80.8	95.3	65.2	93.0	81.2	57.9	72.8	80.6
PointNet++	85.1	82.4	79.0	87.7	77.3	90.8	71.8	91.0	85.9	83.7	95.3	71.6	94.1	91.3	58.7	76.4	82.6
DGCNN	85.2	84.0	83.4	86.7	77.8	90.6	73.5	90.7	83.9	82.8	95.7	66.3	94.9	81.1	63.5	74.5	82.6
LDAGCC	85.1	84.0	83.0	84.9	78.4	90.6	74.4	91.0	88.1	83.4	95.8	67.4	94.9	82.3	59.2	76.0	81.9
3D-GCN	85.1	83.1	84.0	86.6	77.5	90.3	74.1	90.9	86.4	83.8	95.6	66.8	94.8	81.3	59.6	75.7	82.8
SDANet	85.3	—	82.9	84.8	79.0	90.7	68.6	91.0	87.1	82.8	95.6	73.0	95.6	82.5	61.2	76.2	83.1
本文方法	86.0	84.4	81.5	85.0	80.0	91.2	77.4	91.7	88.1	85.1	96.1	73.4	95.0	83.3	60.1	76.9	82.7

方法	mean	mIoU/%
方法	mean	飞机	包	帽子	汽车	椅子	耳机	吉他	刀	灯	电脑	摩托	水杯	手枪	火箭	滑板	桌子
PointNet	83.7	83.4	78.7	82.5	74.9	89.6	73.0	91.5	85.9	80.8	95.3	65.2	93.0	81.2	57.9	72.8	80.6
PointNet++	85.1	82.4	79.0	87.7	77.3	90.8	71.8	91.0	85.9	83.7	95.3	71.6	94.1	91.3	58.7	76.4	82.6
DGCNN	85.2	84.0	83.4	86.7	77.8	90.6	73.5	90.7	83.9	82.8	95.7	66.3	94.9	81.1	63.5	74.5	82.6
LDAGCC	85.1	84.0	83.0	84.9	78.4	90.6	74.4	91.0	88.1	83.4	95.8	67.4	94.9	82.3	59.2	76.0	81.9
3D-GCN	85.1	83.1	84.0	86.6	77.5	90.3	74.1	90.9	86.4	83.8	95.6	66.8	94.8	81.3	59.6	75.7	82.8
SDANet	85.3	—	82.9	84.8	79.0	90.7	68.6	91.0	87.1	82.8	95.6	73.0	95.6	82.5	61.2	76.2	83.1
本文方法	86.0	84.4	81.5	85.0	80.0	91.2	77.4	91.7	88.1	85.1	96.1	73.4	95.0	83.3	60.1	76.9	82.7

方法	OA	mAcc	mIoU
PointNet	—	49.0	41.1
3D-GCN	—	—	53.4
PointCNN	85.9	63.9	57.3
GACNet	87.8	—	62.9
PointASNL	87.7	68.5	62.6
SDANet	—	—	59.6
本文方法	89.3	71.1	65.7

Point cloud classification and segmentation method based on adaptive dynamic graph convolution and parameter-free attention

基于自适应动态图卷积和无参注意力的点云分类分割方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 29

Related Articles 15

Recommended Articles

Metrics

分组	EdgeConv	ADGC	PFA	mAcc	OA
A	√	×	×	90.0	92.7
B	√	×	√	90.4	93.4
C	√	√	×	90.3	93.2
D	√	√	√	91.2	93.8

K	mAcc/%	OA/%	K	mAcc/%	OA/%
5	88.9	92.7	25	89.8	93.4
10	89.7	92.9	30	90.6	93.3
15	91.0	93.3	35	90.0	93.1
20	91.2	93.8	40	89.9	93.0

[1]	Haijie WANG, Guangxin ZHANG, Hai SHI, Shu CHEN. Document-level relation extraction based on entity representation enhancement [J]. Journal of Computer Applications, 2025, 45(6): 1809-1816.
[2]	Daoquan LI, Zheng XU, Sihui CHEN, Jiayu LIU. Network traffic classification model integrating variational autoencoder and AdaBoost-CNN [J]. Journal of Computer Applications, 2025, 45(6): 1841-1848.
[3]	Shuangshuang CUI, Hongzhi WANG, Jiahao ZHU, Hao WU. Two-stage data selection method for classifier with low energy consumption and high performance [J]. Journal of Computer Applications, 2025, 45(6): 1703-1711.
[4]	Sheping ZHAI, Yan HUANG, Qing YANG, Rui YANG. Multi-view entity alignment combining triples and text attributes [J]. Journal of Computer Applications, 2025, 45(6): 1793-1800.
[5]	Jianhua WANG, Chuanyu WU, Liping XU. Enhanced evolutionary algorithm for multi-factor flexible job shop green scheduling [J]. Journal of Computer Applications, 2025, 45(6): 1954-1962.
[6]	Quan WANG, Qixiang LU, Pei SHI. Multi-graph diffusion attention network for traffic flow prediction [J]. Journal of Computer Applications, 2025, 45(5): 1472-1479.
[7]	Hui LI, Bingzhi JIA, Chenxi WANG, Ziyu DONG, Jilong LI, Zhaoman ZHONG, Yanyan CHEN. Generative adversarial network underwater image enhancement model based on Swin Transformer [J]. Journal of Computer Applications, 2025, 45(5): 1439-1446.
[8]	Kai CHEN, Hailiang YE, Feilong CAO. Classification algorithm for point cloud based on local-global interaction and structural Transformer [J]. Journal of Computer Applications, 2025, 45(5): 1671-1676.
[9]	Man CHEN, Xiaojun YANG, Huimin YANG. Pedestrian trajectory prediction based on graph convolutional network and endpoint induction [J]. Journal of Computer Applications, 2025, 45(5): 1480-1487.
[10]	Jie HU, Shuaixing WU, Zhilan CAO, Yan ZHANG. Named entity recognition model based on global information fusion and multi-dimensional relation perception [J]. Journal of Computer Applications, 2025, 45(5): 1511-1519.
[11]	Zihe CHEN, Bin CHEN. Unsupervised point cloud anomaly detection based on multi-representation fusion [J]. Journal of Computer Applications, 2025, 45(5): 1677-1685.
[12]	Dan WANG, Wenhao ZHANG, Lijuan PENG. Channel estimation of reconfigurable intelligent surface assisted communication system based on deep learning [J]. Journal of Computer Applications, 2025, 45(5): 1613-1618.
[13]	Lu CHEN, Huaiyao WANG, Jingyang LIU, Tao YAN, Bin CHEN. Robotic grasp detection with feature fusion of spatial-Fourier domain information under low-light environments [J]. Journal of Computer Applications, 2025, 45(5): 1686-1693.
[14]	Jie HU, Qiyang ZHENG, Jun SUN, Yan ZHANG. Multi-label classification model based on multi-label relational graph and local dynamic reconstruction learning [J]. Journal of Computer Applications, 2025, 45(4): 1104-1112.
[15]	Liqin WANG, Zhilei GENG, Yingshuang LI, Yongfeng DONG, Meng BIAN. Open-world knowledge reasoning model based on path and enhanced triplet text [J]. Journal of Computer Applications, 2025, 45(4): 1177-1183.