基于分级包络域适应的行人轨迹预测模型

李勇明; 李文正; 张小恒; 王品; 胡杰

doi:10.12263/DZXB.20240562

您当前的位置：

首页 >

文章列表页 >

基于分级包络域适应的行人轨迹预测模型

学术论文 | 更新时间：2025-07-24

- 基于分级包络域适应的行人轨迹预测模型
- The Pedestrian Trajectory Prediction Model Based on Hierarchical Envelope Domain Adaptation
- 电子学报 2025年53卷第4期页码：1308-1321
- 作者机构：
  
  重庆大学微电子与通信工程学院，重庆 400044
- 作者简介：
  
  [ "李勇明男，1976年生，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" ]
  [ "李文正男，1999年生，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" ]
  [ "张小恒男，1980年生，四川达州人.重庆大学微电子与通信工程学院博士研究生，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年生，江苏盐城人.重庆大学微电子与通信工程学院副教授，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" ]
  [ "胡杰男，2001年生，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" ]
- 基金信息：
  
  国家自然科学基金(U21A20448;61771080)
- DOI：10.12263/DZXB.20240562
  中图分类号： TP391.4;
- 收稿：2024-06-20，
  
  修回：2025-01-07，
  
  纸质出版：2025-04-25
- 稿件说明：
移动端阅览
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(04): 1308-1321.

LI Yong-ming, LI Wen-zheng, ZHANG Xiao-heng, et al. The Pedestrian Trajectory Prediction Model Based on Hierarchical Envelope Domain Adaptation[J]. Acta Electronica Sinica, 2025, 53(04): 1308-1321.
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(04): 1308-1321. DOI：10.12263/DZXB.20240562

LI Yong-ming, LI Wen-zheng, ZHANG Xiao-heng, et al. The Pedestrian Trajectory Prediction Model Based on Hierarchical Envelope Domain Adaptation[J]. Acta Electronica Sinica, 2025, 53(04): 1308-1321. DOI：10.12263/DZXB.20240562

摘要

复杂环境下行人轨迹短时预测在自动驾驶、社交机器人控制、智能安防及智慧城市等领域有着广泛用途.行人与行人、行人与环境之间的交互具有多尺度复杂性和不确定性，具有挑战.现有深度学习模型虽然有助于挖掘行人的复杂交互关系，但都假设行人轨迹在不同场景遵循相同运动模式，未考虑场景间存在的潜在分布差异；域适应模型虽然考虑了这一点，但仍未考虑行人间和行人环境间的多层次特性.为了解决上述问题，本文提出了一种基于分级包络域适应的行人轨迹预测模型.通过构造局部层次行人邻接关系设计局部层次包络样本，通过个体层次行人关系设计个体层次包络样本，并将两者融合形成双级包络样本.基于双级包络样本构造模块，求得行人轨迹的时空特征分布，从而构造全局层次包络样本.基于注意力机制和跨域分布对齐，分别设计了局部层次包络域适应模块和全局层次包络域适应模块，构建加权预测损失函数将两者融合一体，并联合优化.实验部分选取了2个有代表性的公共数据集，并与5个相关代表性算法模型进行对比.通过消融实验、参数分析、方法对比和轨迹可视化等来进行综合验证.在ETH和UCY的实验结果表明，相比于T-GNN，本文方法的平均位移误差降低了22.7%，终点位移误差降低了19.8%.文章完整版参见链接：

https：//github.com/LWZ9910/MESC-HEDA.git

https://github.com/LWZ9910/MESC-HEDA.git

Abstract

In complex environments

short-term pedestrian trajectory prediction finds extensive applications in autonomous driving

social robotics

intelligent security

and smart city infrastructures. Interactions among pedestrians and between pedestrians and their environment exhibit multi-scale complexities and uncertainties

posing substantial challenges. Although current deep learning models are effective in uncovering complex pedestrian interactions

they typically assume uniform motion patterns across various scenes

thereby neglecting potential distributional discrepancies. While domain adaptation models partially address this issue

they often overlook the mu

lti-level characteristics of pedestrian interactions and environmental influences. To address these challenges

this study proposes a pedestrian trajectory prediction model founded on hierarchical envelope domain adaptation. We design a local-level envelope sample construction module by establishing local-level pedestrian adjacency relationships. An individual-level envelope sample construction module is devised based on individual pedestrian relationships. These two modules are subsequently integrated to form a bi-level envelope sample construction module. Leveraging the bi-level envelope sample construction module

we compute the spatio-temporal feature distribution of all pedestrian trajectories to construct global-level envelope samples. Employing the attention mechanism and cross-domain distribution alignment

we respectively design the local-level envelope domain adaptation and global-level envelope domain adaptation modules. These modules are then integrated into a unified framework using a weighted prediction loss function

which is jointly optimized. The experimental section utilizes two representative public datasets and compares them with five representative algorithm models. Comprehensive validation is conducted through ablation studies

parameter analysis

method comparison

and trajectory visualization. The experimental results in the ETH and UCY datasets show that compared with T-GNN

the average displacement error is reduced by 22.7% and the final displacement error is reduced by 19.8%. For the full version of the article

please refer to the link:

https://github.com/LWZ9910/MESC-HEDA.git

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 Berlin Heidelberg , 2013 : 174 - 183 .

裴炤 , 邱文涛 , 王淼 , 等 . 基于Transformer动态场景信息生成对抗网络的行人轨迹预测方法 [J ] . 电子学报 , 2022 , 50 ( 7 ): 1537 - 1547 .

PEI Z , QIU W T , WANG M , et al . Pedestrian trajectory prediction method using dynamic scene information based transformer generative adversarial network [J ] . Acta Electronica Sinica , 2022 , 50 ( 7 ): 1537 - 1547 . (in Chinese)

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-model SpaceTime interaction [J ] . Acta Electronica Sinica , 2022 , 50 ( 11 ): 2806 - 2812 . (in Chinese)

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 (CVPR) . Piscataway : IEEE , 2022 : 6510 - 6521 .

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

YAN X , KAKADIARIS I A , SHAH S K . Modeling local behavior for predicting social interactions towards human tracking [J ] . Pattern Recognition , 2014 , 47 ( 4 ): 1626 - 1641 .

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 (ICRA) . Piscataway : IEEE , 2014 : 5940 - 5945 .

SCHULZ A T , STIEFELHAGEN R . A controlled interactive multiple model filter for combined pedestrian intention recognition and path prediction [C ] // 2015 IEEE 18th International Conference on Intelligent Transportation Systems . Piscataway : IEEE , 2015 : 173 - 178 .

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 (CVPR) . 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 (WACV) . 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) . Piscataway : IEEE , 2018 : 2684 - 2691 .

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 .

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 (CVPRW) . Piscataway : IEEE , 2019 : 2964 - 2972 .

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 (CVPR) . Piscataway : IEEE , 2019 : 1349 - 1358 .

NIKHIL N , MORRIS B T . Convolutional neural network for trajectory prediction [M ] // Lecture Notes in Computer Science . Cham : Springer International Publishing , 2019 : 186 - 196 .

YAN S J , XIONG Y J , LIN D H . Spatial temporal graph convolutional networks for skeleton-based action recognition [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2018 , 32 ( 1 ): 77 - 82 .

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 (CVPR) . Piscataway : IEEE , 2020 : 14424 - 14432 .

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 (IV) . 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 .

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

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 .

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 .

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 (CVPR) . Piscataway : IEEE , 2021 : 8994 - 9003 .

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 .

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

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 (ICCV) . Piscataway : IEEE , 2019 : 6272 - 6281 .

GIULIARI F , HASAN I , CRISTANI M , et al . Transformer networks for trajectory forecasting [C ] // 2020 25th International Conference on Pattern Recognition (ICPR) . 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

面向集成学习的流形近邻样本包络与分层多类型变换算法

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

基于Transformer动态场景信息生成对抗网络的行人轨迹预测方法