分级包络对抗域适应和松-紧耦合行人轨迹预测模型

李勇明; 胡杰; 张小恒; 王品; 李文正

doi:10.12263/DZXB.20250729

您当前的位置：

首页 >

文章列表页 >

分级包络对抗域适应和松-紧耦合行人轨迹预测模型

学术论文 | 更新时间：2026-02-05

- 分级包络对抗域适应和松-紧耦合行人轨迹预测模型
- Hierarchical Envelope Adversarial Domain Adaptation with Loose-Tight Coupled Trajectory Prediction Model
- 电子学报 2025年53卷第10期页码：3640-3658
- 作者机构：
  
  1.重庆大学微电子与通信工程学院，重庆 400044
  2.重庆开放大学，重庆 400044
- 作者简介：
  
  [ "李勇明男，1976年9月生，四川绵阳人.重庆大学微电子与通信工程学院教授，博士生导师.主要研究方向为医学信号处理、机器学习.E-mail: yongmingli@cqu.edu.cn" ]
  [ "胡杰男，2001年9月生，四川遂宁人.重庆大学微电子与通信工程学院硕士研究生.主要研究方向为图神经网络、行人轨迹预测.E-mail: 2357590375@qq.com" ]
  [ "张小恒男，1980年10月生，四川达州人.博士研究生，副教授.主要研究方向为医学信号处理、机器学习、行人轨迹预测.E-mail: 7818320@qq.com" ]
  [ "王品女，1979年11月生，江苏盐城人. 博士，副教授，硕士生导师. 主要研究方向为图像处理与识别.E-mail: wangpin@cqu.edu.cn" ]
  [ "李文正男，1999年10月生，福建漳州人.重庆大学微电子与通信工程学院硕士研究生.主要研究方向为图神经网络、行人轨迹预测.E-mail: fjxmlwz9910@163.com" ]
- 基金信息：
  
  国家自然科学基金(U21A20448;61771080;72001032)
- DOI：10.12263/DZXB.20250729
  中图分类号： TP391.4;
- 收稿：2025-08-21，
  
  录用：2025-10-24，
  
  纸质出版：2025-10-25
- 稿件说明：
移动端阅览
李勇明, 胡杰, 张小恒, 等. 分级包络对抗域适应和松-紧耦合行人轨迹预测模型[J]. 电子学报, 2025, 53(10): 3640-3658.

LI Yong-ming, HU Jie, ZHANG Xiao-heng, et al. Hierarchical Envelope Adversarial Domain Adaptation with Loose-Tight Coupled Trajectory Prediction Model[J]. Acta Electronica Sinica, 2025, 53(10): 3640-3658.
李勇明, 胡杰, 张小恒, 等. 分级包络对抗域适应和松-紧耦合行人轨迹预测模型[J]. 电子学报, 2025, 53(10): 3640-3658. DOI：10.12263/DZXB.20250729

LI Yong-ming, HU Jie, ZHANG Xiao-heng, et al. Hierarchical Envelope Adversarial Domain Adaptation with Loose-Tight Coupled Trajectory Prediction Model[J]. Acta Electronica Sinica, 2025, 53(10): 3640-3658. DOI：10.12263/DZXB.20250729

摘要

行人轨迹预测在自动驾驶、智能安防及智慧城市等领域有着广泛用途，但是行人交互的复杂性和不确定性使得行人轨迹预测任务至今仍是一个充满挑战的课题.现有行人轨迹预测模型存在以下共性局限性：（1）仅考虑单一的社交耦合关系，不但引入了冗余交互关系，而且未能充分考虑不同场景下轨迹社交耦合关系不同以及行人间耦合关系不一的特性，从而限制了模型对不同场景特征的深度挖掘与有效利用；（2）未充分考虑域偏移问题，极少数方法虽然考虑了域偏移问题，但是采用基于统计准则的域分布对齐方式，对预定义统计度量具有高度依赖性，对复杂多变场景表现出明显的局限性.为了解决上述问题，本文提出了一种基于分级包络对抗域适应和松-紧耦合的行人轨迹预测模型.首先，设计包络样本变换机制构造包络样本并将其拓展到图结构；其次，结合局部域适应和全局域适应，设计对抗域适应模块；此外，针对不同场景下不同耦合关系，构建松-紧耦合包络样本构造模块.实验部分采用了两个代表性的公共数据集进行有效性验证，并与6个相关代表性算法模型进行综合对比.实验结果表明，本文模型比相关算法显著具有更高准确性，ADE（Average Displacement Error）指标与FDE（Final Displacement Error）指标分别下降了17.6%和19.1%，时间开销满足实际需要，这说明本文主要创新点有效.

Abstract

Pedestrian trajectory prediction holds significant applications across autonomous driving

intelligent surveillance

and smart cities. However

the complexity and unpredictability of pedestrian interactions make this task a persistent challenge. Current models face two common limitations: (1) Considering only a single type of social coupling. This introduces redundant interactions. More critically

it fails to account for the varying nature of trajectory coupling across different scenarios and between different pedestrians. Consequently

models cannot deeply explore or effectively utilize diverse scene features; (2) Inadequate handling of domain shift. Although very few methods address domain shift

they rely on statistical criterion-based domain distribution alignment. Such approaches exhibit strong dependency on predefined statistical metrics. This leads to significant limitations in complex

dynamic environments. To address these issues

this paper proposes a hierarchical envelope adversarial domain adaptation with loose-tight coupled model. Firstly

an envelope sample transformation mechanism was designed. It constructs envelope samples and extends them into graph structures; Secondly

an adversarial domain adaptation module was developed. This integrates both local and global domain adaptation strategies; meanwhile

a loose-tight coupling envelope sample construction module was created. It dynamically adapts to diverse coupling relationships across scenarios. These innovations collectively enhance prediction accuracy and robustness. The experimental section employed two representative public datasets for validation and conducted comprehensive comparisons with six relevant baseline algorithms. Results demonstrate that our model achieves significantly higher accuracy compared to existing methods

with the average displacement error (ADE) and final displacement error (FDE) metrics reduced by 17.6% and 19.1%

respectively. The time overhead meets practical requirements

which verifies the effectiveness of our key innovations.

关键词

Keywords

references

孔玮 , 刘云 , 李辉 , 等 . 基于全局自适应有向图的行人轨迹预测 [J ] . 电子学报 , 2022 , 50 ( 8 ): 1905 - 1916 .

KONG W , LIU Y , LI H , et al . Pedestrian trajectory prediction based on global adaptive directed graph [J ] . Acta Electronica Sinica , 2022 , 50 ( 8 ): 1905 - 1916 . (in Chinese)

ZHANG H J , LIU Y J , WANG C , et al . Research on a pedestrian crossing intention recognition model based on natural observation data [J ] . Sensors , 2020 , 20 ( 6 ): 1776 .

MOUSSAÏD M , PEROZO N , GARNIER S , et al . The walking behaviour of pedestrian social groups and its impact on crowd dynamics [J ] . PLoS One , 2010 , 5 ( 4 ): e10047 .

HELBING D , MOLNÁR P . Social force model for pedestrian dynamics [J ] . Physical Review E , 1995 , 51 ( 5 ): 4282 - 4286 .

SCHNEIDER N , GAVRILA D M . Pedestrian path prediction with recursive Bayesian filters: A comparative study [M ] // Pattern Recognition . Berlin : Springer , 2013 : 174 - 183 .

ZHU W J , LIU Y H , ZHANG M Y , et al . Reciprocal consistency prediction network for multi-step human trajectory prediction [J ] . IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 6 ): 6042 - 6052 .

LI Y M , LIANG R Q , WEI W , et al . Temporal pyramid network with spatial-temporal attention for pedestrian trajectory prediction [J ] . IEEE Transactions on Network Science and Engineering , 2022 , 9 ( 3 ): 1006 - 1019 .

桑海峰 , 陈旺兴 , 王海峰 , 等 . 基于多模式时空交互的行人轨迹预测模型 [J ] . 电子学报 , 2022 , 50 ( 11 ): 2806 - 2812 .

SANG H F , CHEN W X , WANG H F , et al . Pedestrian trajectory prediction model based on multi-mode spatio-temporal interaction [J ] . Acta Electronica Sinica , 2022 , 50 ( 11 ): 2806 - 2812 . (in Chinese)

ZHANG C , NI Z J , BERGER C . Spatial-temporal-spectral LSTM: A transferable model for pedestrian trajectory prediction [J ] . IEEE Transactions on Intelligent Vehicles , 2024 , 9 ( 1 ): 2836 - 2849 .

ZHI C Y , SUN H J , XU T . Adaptive trajectory prediction without catastrophic forgetting [J ] . The Journal of Supercomputing , 2023 , 79 ( 14 ): 15579 - 15596 .

LIU Y , ZHANG Y X , LI K M , et al . Knowledge-aware graph transformer for pedestrian trajectory prediction [C ] // 2023 IEEE 26th International Conference on Intelligent Transportation Systems . Piscataway : IEEE , 2024 : 4360 - 4366 .

POIBRENSKI A , NOZARIAN F , REZAEIANARAN F , et al . Uncertainty-aware pseudo labels for domain adaptation in pedestrian trajectory prediction [C ] // 2023 IEEE 26th International Conference on Intelligent Transportation Systems . Piscataway : IEEE , 2024 : 5771 - 5777 .

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 Y M , LI W Z , ZHANG X H , et al . Pedestrian trajectory prediction model based on hierarchical envelope domain adaptation [J ] . Acta Electronica Sinica , 2025 , 53 ( 4 ): 1308 - 1321 . (in Chinese)

FERRER G , SANFELIU A . Behavior estimation for a complete framework for human motion prediction in crowded environments [C ] // 2014 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2014 : 5940 - 5945 .

YANG B , ZHU J R , HU C , et al . Faster pedestrian crossing intention prediction based on efficient fusion of diverse intention influencing factors [J ] . IEEE Transactions on Transportation Electrification , 2024 , 10 ( 4 ): 9071 - 9087 .

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 .

XUE H , HUYNH D Q , REYNOLDS M . SS-LSTM: A hierarchical LSTM model for pedestrian trajectory prediction [C ] // 2018 IEEE Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2018 : 1186 - 1194 .

HUG R , BECKER S , HÜBNER W , et al . Particle-based pedestrian path prediction using LSTM-MDL models [C ] // 2018 21st International Conference on Intelligent Transportation Systems (ITSC) . New York : ACM , 2018 : 2684 - 2691 .

BISAGNO N , ZHANG B , CONCI N . Group LSTM: Group trajectory prediction in crowded scenarios [M ] // Computer Vision - ECCV 2018 Workshops . Cham : Springer , 2019 : 213 - 225 .

YAO Y , ATKINS E , JOHNSON-ROBERSON M , et al . BiTraP: Bi-directional pedestrian trajectory prediction with multi-modal goal estimation [J ] . IEEE Robotics and Automation Letters , 2021 , 6 ( 2 ): 1463 - 1470 .

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 .

SADEGHIAN A , KOSARAJU V , SADEGHIAN A , et al . SoPhie: An attentive GAN for predicting paths compliant to social and physical constraints [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 1349 - 1358 .

AMIRIAN J , HAYET J B , PETTRÉ J . Social ways: Learning multi-modal distributions of pedestrian trajectories with GANs [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Piscataway : IEEE , 2020 : 2964 - 2972 .

JUN O Y , SHI Q W , WANG X X , et al . Pedestrian trajectory prediction based on GAN and attention mechanism [J ] . Laser & Optoelectronics Progress , 2020 , 57 ( 14 ): 141016 .

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 .

LI K M , EIFFERT S , SHAN M , et al . Attentional-GCNN: Adaptive pedestrian trajectory prediction towards generic autonomous vehicle use cases [C ] // 2021 IEEE International Conference on Robotics and Automation . Piscataway : IEEE , 2021 : 14241 - 14247 .

CHEN W X , SANG H F , WANG J Y , et al . DSTCNN: Deformable spatial-temporal convolutional neural network for pedestrian trajectory prediction [J ] . Information Sciences , 2024 , 666 : 120455 .

ZHANG C , BERGER C , DOZZA M . Social-IWSTCNN: A social interaction-weighted spatio- temporal convolutional neural network for pedestrian trajectory prediction in urban traffic scenarios [C ] // 2021 IEEE Intelligent Vehicles Symposium . Piscataway : IEEE , 2021 : 1515 - 1522 .

LV P , WANG W T , WANG Y X , et al . SSAGCN: Social soft attention graph convolution network for pedestrian trajectory prediction [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 35 ( 9 ): 11989 - 12003 .

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 ( 1 ): 2389896 .

PI L , ZHANG Q , YANG L F , et al . Social interaction model enhanced with speculation stage for human trajectory prediction [J ] . Robotics and Autonomous Systems , 2023 , 161 : 104352 .

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 .

MI J , ZHANG X X , ZENG H H , et al . DERGCN: Dynamic-Evolving graph convolutional networks for human trajectory prediction [J ] . Neurocomputing , 2024 , 569 : 127117 .

CHEN W X , SANG H F , WANG J Y , et al . IGGCN: Individual-guided graph convolution network for pedestrian trajectory prediction [J ] . Digital Signal Processing , 2025 , 156 : 104862 .

XU Y , WANG L C , WANG Y Z , et al . Adaptive trajectory prediction via transferable GNN [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2022 : 6510 - 6521 .

HUANG P X , CUI Z H , LI J , et al . Cross-domain trajectory prediction with CTP-Net [M ] // Artificial Intelligence . Cham : Springer , 2022 : 80 - 92 .

HUANG R , TOMPKINS A , PAGNUCCO M , et al . Towards single source domain generalisation in trajectory prediction: A motion prior based approach [C ] // Proceedings of The 2nd Conference on Lifelong Learning Agents . Cambridge : PMLR , 2023 : 227 - 243 .

TANG X Q , SUN W G , HU S Y , et al . MS-net: A multi-path sparse model for motion prediction in multi-scenes [J ] . IEEE Robotics and Automation Letters , 2024 , 9 ( 1 ): 891 - 898 .

GENG M S , LI J Y , LI C J , et al . Adaptive and simultaneous trajectory prediction for heterogeneous agents via transferable hierarchical transformer network [J ] . IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 10 ): 11479 - 11492 .

YANG H F , CHEN Y , CAI J H , et al . Cross-domain pedestrian trajectory prediction via behavioral pattern-aware multi-instance GCN [J ] . Knowledge-Based Systems , 2025 , 329 : 114266 .

MA J , ZHANG Y F , LI Y M , et al . Deep dual-side learning ensemble model for Parkinson speech recognition [J ] . Biomedical Signal Processing and Control , 2021 , 69 : 102849 .

MCCANDLESS D . Knowledge is Beautiful [M ] . London : William Collins , 2014 : 1 - 256 .

ROWLEY J . The wisdom hierarchy: Representations of the DIKW hierarchy [J ] . Journal of Information Science , 2007 , 33 ( 2 ): 163 - 180 .

XIA S Y , LIU Y S , DING X , et al . Granular ball computing classifiers for efficient, scalable and robust learning [J ] . Information Sciences , 2019 , 483 : 136 - 152 .

BOSANCIC B . Information in the knowledge acquisition process [J ] . Journal of Documentation , 2016 , 72 ( 5 ): 930 - 960 .

LI F , ZHANG X H , WANG P , et al . Deep instance envelope network-based imbalance learning algorithm with multilayer fuzzy C-means clustering and minimum interlayer discrepancy [J ] . Applied Soft Computing , 2022 , 123 : 108846 .

LI F , LI Y M , SHEN Y H , et al . Deep fuzzy envelope sample generation mechanism for imbalanced ensemble classification [J ] . IEEE Transactions on Fuzzy Systems , 2024 , 32 ( 3 ): 1248 - 1262 .

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 , 2010 : 261 - 268 .

LERNER A , CHRYSANTHOU Y , LISCHINSKI D . Crowds by example [J ] . Computer Graphics Forum , 2007 , 26 ( 3 ): 655 - 664 .

李勇明 , 李文正 , 张小恒 , 等 . 一种基于分级包络域适应的行人轨迹预测方法 : CN118918140A [P ] . 2024-11-04 .

LI Y M , LI W Z , ZHANG X H , et al . A pedestrian trajectory prediction approach based on hierarchical envelope domain adaptation : CN118918140A [P ] . 2024-11-04 . (in Chinese)

LIU S H , LIU H B , WANG Y S , et al . MDST-DGCN: A multilevel dynamic spatiotemporal directed graph convolutional network for pedestrian trajectory prediction [J ] . Computational Intelligence and Neuroscience , 2022 , 2022 ( 1 ): 4192367 .

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 .

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 , 2020 : 6271 - 6280 .

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 .

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

基于分级包络域适应的行人轨迹预测模型

基于特征异常检测与伪标签回归的无监督对抗域适应

基于第一视角的非自回归行人轨迹预测模型

基于多模式时空交互的行人轨迹预测模型

Xe^1v离子激光感生荧光用于医用X射线ZnCdS:Ag荧光屏的性能研究