Research on pedestrian trajectory prediction method based on social attention mechanism

被引：0

作者：

Li L. ^{[1
,2
]}

Zhou B. ^{[1
]}

Lian J. ^{[1
,2
]}

Zhou Y. ^{[1
]}

机构：

[1] School of Automotive Engineering, Dalian University of Technology, Dalian

[2] State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology, Dalian

来源：

Tongxin Xuebao/Journal on Communications | 2020年 / 41卷 / 06期

基金：

中国国家自然科学基金;

关键词：

Attention mechanism; Generative adversarial network; Optimal pooling model; Pedestrian trajectory prediction; Social force model;

D O I：

10.11959/j.issn.1000-436x.2020100

中图分类号：

学科分类号：

摘要：

In order to improve the speed, accuracy and model interpretability of trajectory prediction in pedestrian interaction, a GAN model based on social attention mechanism was proposed. Firstly, a new type of social relationship on pedestrians was defined to model social relationships and a network model based on the attention mechanism was designed to improve the speed and interpretability of network prediction. Secondly, the influence of different pooling mechanisms on the prediction results was explored to determine the pooling model with excellent performance. Finally, a trajectory prediction network was built on this basis and trained on the UCY and ETH data sets. The experimental results show that the model not only has better prediction accuracy than the existing methods, but also improves the real-time performance by 18.3% compared with the existing methods. © 2020, Editorial Board of Journal on Communications. All right reserved.

引用

页码：175 / 183

页数：8

共 23 条

[1]

DAI M, WANG J, YIN G, Et al., Dynamic output-feedback robust control for vehicle path tracking considering different human drivers' characteristics, Technical Committee on Control Theory, pp. 1157-1162, (2017)

[2]

MEHDI M, NIRIASKA P, SIMON G, Et al., The walking behaviour of pedestrian social groups and its impact on crowd dynamics, Plos One, 5, 4, (2010)

[3]

KITANI K, ZIEBART B, BAGNELL J A, Et al., Activity forecasting, Proceedings of the 12th European conference on Computer Vision - Volume Part IV, pp. 201-214, (2012)

[4]

LEE N, CHOI W, VERNAZA P, Et al., Desire: distant future prediction in dynamic scenes with interacting agents, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 336-345, (2017)

[5]

YAMAGUCHI K, BERG A C, ORTIZ L E, Et al., Who are you with and where are you going?, Computer Vision and Pattern Recognition, pp. 1345-1352, (2011)

[6]

HOCHREITER S, SCHMIDHUBER J., Long short-term memory, Neural Computation, 9, 8, (1997)

[7]

ALAHI A, GOEL K, RAMANATHAN V, Et al., Social LSTM: human trajectory prediction in crowded spaces, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961-971, (2016)

[8]

GUPTA A, JOHNSON J, FEI-FEI L, Et al., Social GAN: socially acceptable trajectories with generative adversarial networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2255-2264, (2018)

[9]

GOODFELLOW I, POUGET-ABADIE J, MIRZA M, Et al., Generative adversarial nets, Advances in Neural Information Processing Systems, pp. 2672-2680, (2014)

[10]

SADEGHIAN A, KOSARAJU V, SADEGHIAN A, Et al., SoPhie: an attentive GAN for predicting paths compliant to social and physical constraints, (2018)

← 1 2 3 →