基于自适应群体掩码图卷积网络的行人轨迹预测

陈旺兴; 桑海峰; 刘晴

doi:10.12263/DZXB.20251200

您当前的位置：

首页 >

文章列表页 >

基于自适应群体掩码图卷积网络的行人轨迹预测

学术论文 | 更新时间：2026-05-28

- 基于自适应群体掩码图卷积网络的行人轨迹预测
- Adaptive Group Masked Graph Convolution Network for Pedestrian Trajectory Prediction
- 电子学报 2026年54卷第2期页码：774-784
- 作者机构：
  
  沈阳工业大学信息科学与工程学院，辽宁沈阳 110870
- 作者简介：
  
  [ "陈旺兴男，1998年3月出生于江西省抚州市。现为沈阳工业大学博士研究生。主要研究方向为轨迹预测、智能驾驶。E-mail: chenwangxing@smail.sut.edu.cn" ]
  [ "桑海峰男，1978年1月出生于辽宁省沈阳市。现为沈阳工业大学教授、博士生导师。主要研究方向为机器视觉检测技术和智能视频分析技术。E-mail: sanghaif@163.com" ]
  [ "刘晴女，1994年3月出生于辽宁省沈阳市。现为沈阳工业大学讲师。主要研究方向为机器视觉检测与图像识别、人工智能与医药交叉领域。E-mail: Lqing0304@126.com" ]
- 基金信息：
  
  辽宁省科技厅重点研发项目(2024JH2/102400028);辽宁省教育厅科研项目(YTMS20231210)
- DOI：10.12263/DZXB.20251200
  中图分类号： TP391.4;
- 收稿：2026-01-16，
  
  录用：2026-02-11，
  
  纸质出版：2026-02-25
- 稿件说明：
移动端阅览
陈旺兴, 桑海峰, 刘晴. 基于自适应群体掩码图卷积网络的行人轨迹预测[J]. 电子学报, 2026, 54(02): 774-784.

CHEN Wangxing, SANG Haifeng, LIU Qing. Adaptive Group Masked Graph Convolution Network for Pedestrian Trajectory Prediction[J]. Acta Electronica Sinica, 2026, 54(02): 774-784.
陈旺兴, 桑海峰, 刘晴. 基于自适应群体掩码图卷积网络的行人轨迹预测[J]. 电子学报, 2026, 54(02): 774-784. DOI：10.12263/DZXB.20251200

CHEN Wangxing, SANG Haifeng, LIU Qing. Adaptive Group Masked Graph Convolution Network for Pedestrian Trajectory Prediction[J]. Acta Electronica Sinica, 2026, 54(02): 774-784. DOI：10.12263/DZXB.20251200

摘要

行人轨迹预测对于提升自动驾驶和服务机器人的决策能力以及降低未来潜在碰撞风险方面具有重要意义。然而，由于行人群体内外社会交互关系的差异性和复杂性，现有研究往往未能对群内和群外交互关系进行显式区分与独立建模，不同类型交互特征在模型学习过程中相互混淆，难以精准刻画行人在复杂场景下的真实运动模式，进而制约了模型预测性能的进一步提升。因此，本文提出了一种基于自适应群体掩码图卷积网络（Adaptive Group Masked Graph Convolution Network，AGMGCN）的行人轨迹预测模型，通过对群内和群外交互关系进行独立建模，从而提升模型轨迹预测的准确性。该模型首先构建社会图并采用自注意力机制进行处理，以获得注意力矩阵用于初步表示行人之间的交互关系。后续设计了时频域卷积模块，通过在时域和频域同时对注意力矩阵进一步处理，生成用于表征行人时空交互关系的时频交互矩阵，以实现对行人复杂动态交互更准确的刻画。为有效区分并独立建模群内和群外交互，模型设计了自适应群体掩码模块，根据行人之间的特征相似性自适应确定阈值，并通过阈值处理生成群内掩码矩阵和群外掩码矩阵，为后续群内和群外交互关系的独立建模提供支持。在此基础上，将时频交互矩阵与群外和群内掩码矩阵相结合，并分别应用图卷积捕捉群内交互特征和群外交互特征，从而实现行人群内和群外交互关系的独立建模。最后，模型设计了特征融合模块动态加权融合群内交互特征和群外交互特征，并通过时间卷积网络完成行人未来轨迹的预测。在ETH、UCY和SDD数据集上的实验结果表明，在仅使用23.9 K模型参数的条件下，本文提出的方法相较于DSTIGCN在平均位移误差和终点位移误差上分别降低了12%和20%，验证了所提方法在预测精度和计算成本方面的优势。

Abstract

Pedestrian trajectory prediction is crucial for improving the decision-making capabilities of autonomous vehicles and service robots

as well as mitigating potential future collision risks. However

due to the differences and complexity of social interactions within and outside pedestrian groups

existing studies often fail to explicitly distinguish and independently model interactions within and outside groups. This leads to confusion of different types of interaction features during model learning

making it difficult to accurately depict the real motion patterns of pedestrians in complex scenarios

thus restricting further improvement in model prediction performance. Therefore

this paper proposes a pedestrian trajectory prediction model based on an adaptive group masked graph convolution network (AGMGCN). By independently modeling in-group and out-group interactions

the accuracy of model trajectory prediction is improved. The model first constructs a social graph and processes it using a self-attention mechanism to obtain an attention matrix that initially represents the interactions between pedestrians. Subsequently

a time-frequency domain convolution module is designed to further process the attention matrix in both the time and frequency domains

generating a time-frequency interaction matrix to characterize the spatial-temporal interactions of pedestrians

thus achieving a more accurate portrayal of complex dynamic interactions. To effectively distinguish and independently model in-group and out-group interactions

an adaptive group masking module is designed. This module adaptively determines a threshold based on the feature similarity between pedestrians and generates in-group and out-group masking matrices through threshold processing

providing support for the subsequent independent modeling of in-group and out-group interactions. Building upon this foundation

the time-frequency interaction matrix is combined with out-group and in-group masking matrices

and graph convolution is applied to respectively capture in-group and out-group interaction features

thereby achieving independent modeling of pedestrian in-group and out-group interaction relationships. Finally

a feature fusion module is designed to dynamically weight and fuse in-group and out-group interaction features and then temporal convolution networks are used to predict the future trajectory of pedestrians. Experimental results on the ETH

UCY and SDD datasets demonstrate that

with only 23.9 K model parameters

the proposed method reduces the average displacement error by 12% and the final displacement error by 20% compared to DSTIGCN

validating the advantages of the proposed method in terms of prediction accuracy and computational cost.

关键词

Keywords

references

李勇明 , 李文正 , 张小恒 , 等 . 基于分级包络域适应的行人轨迹预测模型 [J ] . 电子学报 , 2025 , 53 ( 4 ): 1308 - 1321 .

Li Yongming , Li Wenzheng , Zhang Xiaoheng , et al . The pedestrian trajectory prediction model based on hierarchical envelope domain adaptation [J ] . Acta Electronica Sinica , 2025 , 53 ( 4 ): 1308 - 1321 . (in Chinese)

Bhaskara R , Viswanath H , Bera A . Trajectory prediction for robot navigation using flow-guided Markov neural operator [C ] // 2024 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2024 : 15209 - 15216 . DOI: 10.1109/icra57147.2024.10611154 http://dx.doi.org/10.1109/icra57147.2024.10611154

Korbmacher R , Tordeux A . Review of pedestrian trajectory prediction methods: Comparing deep learning and knowledge-based approaches [J ] . IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 12 ): 24126 - 24144 . DOI: 10.1109/tits.2022.3205676 http://dx.doi.org/10.1109/tits.2022.3205676

孔玮 , 刘云 , 李辉 , 等 . 基于深度学习的行人轨迹预测方法综述 [J ] . 控制与决策 , 2021 , 36 ( 12 ): 2841 - 2850 .

Kong Wei , Liu Yun , Li Hui , et al . Survey of pedestrian trajectory prediction methods based on deep learning [J ] . Control and Decision , 2021 , 36 ( 12 ): 2841 - 2850 . (in Chinese)

Alahi A , Goel K , Ramanathan V , et al . Social LSTM: Human trajectory prediction in crowded spaces [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2016 : 961 - 971 . DOI: 10.1109/cvpr.2016.110 http://dx.doi.org/10.1109/cvpr.2016.110

Zhang P , Ouyang W L , Zhang P F , et al . SR-LSTM: State refinement for LSTM towards pedestrian trajectory prediction [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 : 12077 - 12086 . DOI: 10.1109/cvpr.2019.01236 http://dx.doi.org/10.1109/cvpr.2019.01236

Gupta A , Johnson J , Li F F , et al . Social GAN: Socially acceptable trajectories with generative adversarial networks [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 2255 - 2264 . DOI: 10.1109/cvpr.2018.00240 http://dx.doi.org/10.1109/cvpr.2018.00240

Vemula A , Muelling K , Oh J . Social attention: Modeling attention in human crowds [C ] // 2018 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2018 : 4601 - 4607 . DOI: 10.1109/icra.2018.8460504 http://dx.doi.org/10.1109/icra.2018.8460504

Yu C J , Ma X , Ren J W , et al . Spatio-temporal graph transformer networks for pedestrian trajectory prediction [C ] // Computer Vision - ECCV 2020 . Cham : Springer , 2020 : 507 - 523 . DOI: 10.1007/978-3-030-58610-2_30 http://dx.doi.org/10.1007/978-3-030-58610-2_30

Giuliari F , Hasan I , Cristani M , et al . Transformer networks for trajectory forecasting [C ] // 2020 25th International Conference on Pattern Recognition . Piscataway : IEEE , 2021 : 10335 - 10342 . DOI: 10.1109/icpr48806.2021.9412190 http://dx.doi.org/10.1109/icpr48806.2021.9412190

Yuan Y , Weng X S , Ou Y L , et al . AgentFormer: Agent-aware transformers for socio-temporal multi-agent forecasting [C ] // 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 9793 - 9803 . DOI: 10.1109/iccv48922.2021.00967 http://dx.doi.org/10.1109/iccv48922.2021.00967

Sang H F , Chen W X , Zhao Z S . Review of pedestrian trajectory prediction based on graph neural networks [J ] . Information Fusion , 2026 , 127 : 103727 . DOI: 10.1016/j.inffus.2025.103727 http://dx.doi.org/10.1016/j.inffus.2025.103727

Huang Y F , Bi H K , Li Z X , et al . STGAT: Modeling spatial-temporal interactions for human trajectory prediction [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 6271 - 6280 . DOI: 10.1109/iccv.2019.00637 http://dx.doi.org/10.1109/iccv.2019.00637

Mohamed A , Qian K , Elhoseiny M , et al . Social-STGCNN: A social spatio-temporal graph convolutional neural network for human trajectory prediction [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 14412 - 14420 . DOI: 10.1109/cvpr42600.2020.01443 http://dx.doi.org/10.1109/cvpr42600.2020.01443

Shi L S , Wang L , Long C J , et al . SGCN: Sparse graph convolution network for pedestrian trajectory prediction [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2021 : 8990 - 8999 . DOI: 10.1109/cvpr46437.2021.00888 http://dx.doi.org/10.1109/cvpr46437.2021.00888

Chen W X , Sang H F , Wang J Y , et al . IMGCN: Interpretable masked graph convolution network for pedestrian trajectory prediction [J ] . Transportmetrica B: Transport Dynamics , 2024 , 12 : 2389896 . DOI: 10.1080/21680566.2024.2389896 http://dx.doi.org/10.1080/21680566.2024.2389896

Chen W X , Sang H F , Wang J Y , et al . DSTIGCN: Deformable spatial-temporal interaction graph convolution network for pedestrian trajectory prediction [J ] . IEEE Transactions on Intelligent Transportation Systems , 2025 , 26 ( 5 ): 6923 - 6935 . DOI: 10.1109/tits.2024.3525080 http://dx.doi.org/10.1109/tits.2024.3525080

Cao D F , Li J C , Ma H B , et al . Spectral temporal graph neural network for trajectory prediction [C ] // 2021 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2021 : 1839 - 1845 . DOI: 10.1109/icra48506.2021.9561461 http://dx.doi.org/10.1109/icra48506.2021.9561461

Chen W X , Sang H F , Wang J Y , et al . WTGCN: Wavelet transform graph convolution network for pedestrian trajectory prediction [J ] . International Journal of Machine Learning and Cybernetics , 2024 , 15 ( 12 ): 5531 - 5548 . DOI: 10.1007/s13042-024-02258-5 http://dx.doi.org/10.1007/s13042-024-02258-5

Xu C X , Li M S , Ni Z Y , et al . GroupNet: Multiscale hypergraph neural networks for trajectory prediction with relational reasoning [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 6488 - 6497 . DOI: 10.1109/cvpr52688.2022.00639 http://dx.doi.org/10.1109/cvpr52688.2022.00639

Xu C X , Wei Y X , Tang B H , et al . Dynamic-group-aware networks for multi-agent trajectory prediction with relational reasoning [J ] . Neural Networks , 2024 , 170 : 564 - 577 . DOI: 10.1016/j.neunet.2023.11.005 http://dx.doi.org/10.1016/j.neunet.2023.11.005

Zhou L , Zhao Y L , Yang D Y , et al . GCHGAT: Pedestrian trajectory prediction using group constrained hierarchical graph attention networks [J ] . Applied Intelligence , 2022 , 52 ( 10 ): 11434 - 11447 . DOI: 10.1007/s10489-021-02997-w http://dx.doi.org/10.1007/s10489-021-02997-w

Bengio Y , Léonard N , Courville A . Estimating or propagating gradients through stochastic neurons for conditional computation [PP/OL ] . V1. arVix . ( 2013-08-15 )[ 2026-01-16 ] . https://arxiv.org/abs/1308.3432 https://arxiv.org/abs/1308.3432 .

Sang H F , Chen W X , Wang J Y , et al . RDGCN: Reasonably dense graph convolution network for pedestrian trajectory prediction [J ] . Measurement , 2023 , 213 : 112675 . DOI: 10.1016/j.measurement.2023.112675 http://dx.doi.org/10.1016/j.measurement.2023.112675

Uhlemann N , Fent F , Lienkamp M . Evaluating pedestrian trajectory prediction methods with respect to autonomous driving [J ] . IEEE Transactions on Intelligent Transportation Systems , 2024 , 25 ( 10 ): 13937 - 13946 . DOI: 10.1109/tits.2024.3386195 http://dx.doi.org/10.1109/tits.2024.3386195

Pellegrini S , Ess A , Schindler K , et al . You’ll never walk alone: Modeling social behavior for multi-target tracking [C ] // 2009 IEEE 12th International Conference on Computer Vision . Piscataway : IEEE , 2009 : 261 - 268 . DOI: 10.1109/iccv.2009.5459260 http://dx.doi.org/10.1109/iccv.2009.5459260

Lerner A , Chrysanthou Y , Lischinski D . Crowds by example [J ] . Computer Graphics Forum , 2007 , 26 ( 3 ): 655 - 664 . DOI: 10.1111/j.1467-8659.2007.01089.x http://dx.doi.org/10.1111/j.1467-8659.2007.01089.x

Robicquet A , Sadeghian A , Alahi A , et al . Learning social etiquette: Human trajectory understanding in crowded scenes [M ] // Computer vision - ECCV 2016 . Cham : Springer International Publishing , 2016 : 549 - 565 . DOI: 10.1007/978-3-319-46484-8_33 http://dx.doi.org/10.1007/978-3-319-46484-8_33

Monti A , Bertugli A , Calderara S , et al . DAG-net: Double attentive graph neural network for trajectory forecasting [C ] // 2020 25th International Conference on Pattern Recognition . Piscataway : IEEE , 2021 : 2551 - 2558 . DOI: 10.1109/icpr48806.2021.9412114 http://dx.doi.org/10.1109/icpr48806.2021.9412114

Mohamed A , Zhu D , Vu W , et al . Social-implicit: Rethinking trajectory prediction evaluation and the effectiveness of implicit maximum likelihood estimation [M ] // Computer vision - ECCV 2022 . Cham : Springer Nature Switzerland , 2022 : 463 - 479 . DOI: 10.1007/978-3-031-20047-2_27 http://dx.doi.org/10.1007/978-3-031-20047-2_27

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向大模型预训练的多模态行人轨迹预测隐私保护方案

分级包络对抗域适应和松-紧耦合行人轨迹预测模型

基于分级包络域适应的行人轨迹预测模型

基于第一视角的非自回归行人轨迹预测模型

结合频域物理感知与高阶语义融合的一体化遥感图像复原框架