Citation

Zhang P, Xue J, Zhang P, Zheng N, Ouyang W. IEEE Trans. Pattern Anal. Mach. Intell. 2020; ePub(ePub): ePub.

Copyright

(Copyright © 2020, Institute of Electrical and Electronics Engineers, Publisher IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/TPAMI.2020.3038217

PMID

33196437

Abstract

In the task of pedestrian trajectory prediction, social interaction could be one of the most complicated factors. Recent studies have shown a great ability of LSTM networks in learning social behaviors from datasets, e.g., introducing LSTM hidden states of the neighbors at the last time step into LSTM recursion. However, those methods depend on previous neighboring features which lead to a delayed observation. In this paper, we propose a data-driven states refinement LSTM network (SR-LSTM) to enable the utilization of the current intention of neighbors through a message passing framework. Moreover, the model performs in the form of self-updating by jointly refining the current states of all participants, rather than feature concatenations. In the process of states refinement, a social-aware information selection module consisting of an element-wise motion gate and a pedestrian-wise attention is designed as the guidance of the message passing process. Considering the pedestrian walking space as a graph, spatial-edge LSTMs are exploited to enhance the model capacity, where two kinds of LSTMs interact with each other so that states of them are interactively refined. Experimental results on four widely used pedestrian trajectory datasets, ETH, UCY, PWPD, and NYGC demonstrate the effectiveness of the proposed model.

Language: en