科学技术与应用

基于全局时序注意力的行人轨迹预测方法

成 洋

湖北孝感美珈职业学院

钟 珞

湖北孝感美珈职业学院

DOI: https://doi.org/10.59429/kxjsyy.v3i5.15734

Keywords: 行人轨迹预测；Transformer；全局时序注意力；优化

---

Abstract

随着自动驾驶、物联网等技术的发展，行人轨迹预测在城市交通疏导、自动驾驶、机器人等领域应用前景广 泛。行人运动的突变性与交互复杂性使轨迹预测极具挑战。针对现有 Transformer 模型仅利用前段轨迹特征、忽略 后段特征、在不规则运动上预测效果差的问题，本文提出基于全局时序注意力优化的行人轨迹预测方法（GTAO）。 GTAO 通过全局时序指导模块实现前、后段序列轨迹的互相优化，并以真实值监督训练，提升鲁棒性与泛化能力。 在 ETH 和 UCY 上的实验表明，GTAO 定性与定量结果均优于基线，指标提升 4%~6%。

---

References

[1] Schneider N, Gavrila D M. Pedestrian path prediction with recursive bayesian filters: A comparative study[C]. Pattern Recognition: 35th German Conference, GCPR September 3-6, 2013: 174-183.

[2] Pavlovic V, Rehg J M, MacCormick J. Learning switching linear models of human motion[J]. Advances in neural information processing systems, 2000, 13.

[3] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.

[4] Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018.

[5] Lan Z, Chen M, Goodman S, et al. Albert: A lite bert for self-supervised learning of language representations[J]. arXiv preprint arXiv:1909.11942, 2019.

[6] Yang Z, Dai Z, Yang Y, et al. generalized autoregressive pretraining for language understanding; 2019[J]. Preprint at https: arxiv. org abs 1906.08237 Accessed June, 2021, 21.

[7] Young T, Hazarika D, Poria S, et al. Recent trends in deep learning based natural language processing[J]. IEEE Computational intelligenCe magazine, 2018, 13(3): 55-75.

[8] Yu C, Ma X, Ren J, et al. Spatio-temporal graph transformer networks for pedestrian trajectory prediction[C]. Proceedings of the IEEE CVF European Conference on Computer Vision(ECCV), 2020: 507-523.

[9] Pellegrini S, Ess A, Schindler K, et al. You'll never walk alone: Modeling social behavior for multi-target tracking[C]. Proceedings of the IEEE CVF International Conference on Computer Vision(ICCV). 2009: 261-268.

[10] Lerner A, Chrysanthou Y, Lischinski D. Crowds by example[C]. Computer graphics forum. Oxford, UK: Blackwell Publishing Ltd, 2007, 26(3): 655-664.