Abstract
Pedestrian trajectory prediction is important for understanding human social behavior. Since the complex nature of the crowd dynamics, it remains a challenging work. Recent studies based on LSTM or GAN have made great progress in sequence prediction, but they still suffer from limitations of modeling neighborhood and handling pedestrian interaction. To address these problems, we propose a conflict-avoiding approach to predict pedestrians’ trajectories based on the Delaunay triangulation graph, which can model the crowd hierarchically. Meanwhile, the middle-level semantic feature is adopted to represent pedestrians’ dynamic interactions in Delaunay triangulation graph. Besides, to evaluate the effect of an additional semantic feature for LSTM, we add an information selection mechanism of pedestrian motion which updates the cell state of LSTM with a new social conflict gate. Furthermore, the results on two public datasets, BIWI and UCY, reveal that the proposed conflict-avoiding approach is excellent in terms of stability and validity. Our experimental results demonstrate that our method can predict the same time span using shorter observation period than state-of-the-art algorithms.
Similar content being viewed by others
References
Chen Z, Zhang Y, Wu C, Ran B (2019) Understanding individualization driving states via latent dirichlet allocation model. IEEE Intell Transport Syst Magaz 11(2):41–53
Qiao S, Tang C, Jin H et al (2010) PutMode: prediction of uncertain trajectories in moving objects databases. Appl Intell 33:370–386
Chen Z, Cai H, Zhang Y, Wu C, Mu M, Li Z, Sotelo MA (2019) A novel sparse representation model for pedestrian abnormal trajectory understanding. In: Expert Systems with Applications, 138
Khodabandelou G, Kheriji W, Selem FH (2020) Link traffic speed forecasting using convolutional attention-based gated recurrent unit. Appl Intell
Yamaguchi K, Berg AC, Ortiz LE, Berg TL (2011) Who are you with and Where are you going?. In: IEEE conference on computer vision and pattern recognition (CVPR)
Alahi A, Goel K, Ramannathan V, Robicquet A, Fei-Fei L, Savarese S (2016) Social LSTM: Human trajectory prediction in crowded spaces. In: IEEE conference on computer vision and pattern recognition (CVPR)
Varshneya D, Srinivasaraghavan G (2017) Human trajectory prediction using spatially aware deep attention models. In: 31st Conference on neural information processing systems (NIPS)
Alahi A, Ramanathan V, Goel K, Robicquet A, Sadeghian A, Li F-F, Savarese S (2017) Learning to predict human behaviour in crowded scenes. In: Group and crowd behavior for computer vision
Zhang P, Ouyang W, Zhang P, Xue J (2019) SR-LSTM: State refinement for LSTM towards pedestrian trajectory prediction. In: IEEE Conference on computer vision and pattern recognition (CVPR)
Pajouheshgar E, Lampert CH (2018) Back to square one: Probabilistic trajectory forecasting without bells and whistles. In: 32nd Conference on neural information processing systems (NIPS)
Helbing D, Molnar P (1995) Social force model for pedestrian dynamics. Phys Rev E 51 (5):4282–4286
Gupta A, Johnson J, Li F-F, Savarese S, Alahi A (2018) Social GAN: Socially acceptable trajectories with generative adversarial networks. In: IEEE Conference on computer vision and pattern recognition (CVPR)
Alahi A, Ramanathan V, Li F-F (2014) Socially-aware large-scale crowd forecasting. In: IEEE Conference on computer vision and pattern recognition (CVPR)
Xu Y, Zhixin P, Gao S (2018) Encoding crowd interaction with DNN for pedestrian trajectory prediction. In: IEEE Conference on computer vision and pattern recognition (CVPR)
Vemula A, Muelling K, Oh J (2018) Social attention: Modeling attention in human crowds. In: IEEE International conference on robotics and automation (ICRA), 1–7
Jain A, Zamir AR, Savarese S, Saxena A (2016) Structural-RNN: Deep learning on spatio-temporal graphs. In: IEEE Conference on computer vision and pattern recognition (CVPR)
Nikhil N, Tran Morris B (2018) Convolutional neural network for trajectory prediction. In: European conference on computer vision – ECCV 2018 workshops
Bartoli F, Lisanti G, Ballan L, Del Bimbo A (2018) Context-aware trajectory prediction in crowded spaces. In: 24th International conference on pattern recognition
Haddad S, Wu M, Wei H, Lam SK (2019) Situation-aware pedestrian trajectory prediction with spatio-temporal attention model. In: 24th Computer vision winter workshop (CVWW)
Sadeghian A, Kosaraju V, Sadeghian A, Hirose N, Rezatofighi H, Savarese S (2019) SoPhie: An Attentive GAN for predicting paths compliant to social and physical constraints. In: IEEE/CVF Conference on computer vision and pattern recognition (CVPR)
Huynh M, Gita A (2018) Scene-LSTM: A model for human trajectory prediction. arXiv:1808.04018
Fradi H, Luvison B, Pham QC (2016) Crowd behavior analysis using local mid-level visual descriptors. In: IEEE Transactions on circuits and systems for video technology, vol. 27
Mikolov T, Karafiat M, Burget L, Cernock H, Khudanpur S (2010) Recurrent neural network based language model. In: Eleventh annual conference of the international speech communication association
Hochreiter S, Schmidhuber J (1997) Long short-term memory. In: IEEE Transactions on circuits and systems for video technology, vol. 9
Graves A (2013) Generating sequences with recurrent neural networks. Comput Sci
Pellegrini S, Ess A, Schindler K, Van Gool L (2009) You’ll never walk alone: Modeling social behavior for multi-targer tracking. In: IEEE 12th international conference on computer vision (ICCV)
Lerner A, Chrysanthou Y, Lischinski D (2007) Crowds by example. Comput Graph Forum 26(3):655–664
Liang J, Jiang L, Niebles JC, Hauptmann AG, Li F-F (2019) Peeking into the future: Predicting future person activities and locations in videos. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR)
Sun J, Jiang Q, Lu C (2020) Recursive social behavior graph for trajectory prediction. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR)
Fang L, Jiang Q, Shi J, Zhou B (2020) TPNet: trajectory proposal network for motion prediction. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR)
Acknowledgments
This work is supported by the Fundamental Research Funds for the Central Universities (2019YJS043).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ma, Q., Zou, Q., Huang, Y. et al. Dynamic pedestrian trajectory forecasting with LSTM-based Delaunay triangulation. Appl Intell 52, 3018–3028 (2022). https://doi.org/10.1007/s10489-021-02562-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02562-5