Pedestrian Trajectory Prediction Based on Deep Convolutional LSTM Network

doi:10.1109/TITS.2020.2981118

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	Pedestrian Trajectory Prediction Based on Deep Convolutional LSTM Network
	Song, Xiao 1; Chen, Kai 1; Li, Xu 2; Sun, Jinghan 3; Hou, Baocun 4; Cui, Yong 1; Zhang, Baochang 1; Xiong, Gang 5; Wang, Zilie 6
刊名	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
	2021-06-01
卷号	22 期号:6 页码:3285-3302
关键词	Trajectory Predictive models Neural networks Force Mathematical model Feature extraction Tensors Pedestrian behavior convolution long short-term memory neural network
ISSN号	1524-9050
DOI	10.1109/TITS.2020.2981118
通讯作者	Chen, Kai(chenkaivisual@buaa.edu.cn)
英文摘要	Pedestrian trajectory prediction is vital for transportation systems. Generally we can divide pedestrian behavior modeling into two categories, i.e., knowledge-driven and data-driven. The former might bring expert bias, and it sometimes generates unrealistic pedestrian movement due to unnecessary repulsive forces. The latter approach is popular nowadays but most existing neural networks, including fully connected long short-term memory (LSTM) networks, use a 1D vector to model their input and state. The shortcoming is that these works cannot learn spatial information about pedestrians, especially in a dense crowd. To tackle this, we propose to use tensors to represent essential environment features of pedestrians. Accordingly, a convolutional LSTM is designed and deepened to predict spatiotemporal trajectory sequences. As the tensor and convolution can learn better spatiotemporal interactions among pedestrians and environments, experimental results show that the proposed network can estimate more realistic trajectories for a dense crowd in evacuation and counterflow.
资助项目	National Key Research and Development Program of China[2018YFB1702703] ; Open Fund of China State Key Laboratory of Intelligent Manufacturing System Technology ; Fundamental Research Funds for the Central Universities
WOS关键词	CROWD DYNAMICS ; EVACUATION ; MANAGEMENT ; SIMULATION ; MODELS
WOS研究方向	Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000658360600006
资助机构	National Key Research and Development Program of China ; Open Fund of China State Key Laboratory of Intelligent Manufacturing System Technology ; Fundamental Research Funds for the Central Universities
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45343]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Chen, Kai
作者单位	1.Beihang Univ, Sch Automat, Beijing 100083, Peoples R China 2.China State Key Lab Intelligent Mfg Syst Technol, Beijing 100854, Peoples R China 3.Univ Illinois, Dept Comp Sci, Champaign, IL 61820 USA 4.Beijing Aerosp Smart Mfg Technol Dev Co Ltd, Beijing, Peoples R China 5.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 6.Beihang Univ, Sch Software, Beijing 100083, Peoples R China
推荐引用方式 GB/T 7714	Song, Xiao,Chen, Kai,Li, Xu,et al. Pedestrian Trajectory Prediction Based on Deep Convolutional LSTM Network[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2021,22(6):3285-3302.
APA	Song, Xiao.,Chen, Kai.,Li, Xu.,Sun, Jinghan.,Hou, Baocun.,...&Wang, Zilie.(2021).Pedestrian Trajectory Prediction Based on Deep Convolutional LSTM Network.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,22(6),3285-3302.
MLA	Song, Xiao,et al."Pedestrian Trajectory Prediction Based on Deep Convolutional LSTM Network".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 22.6(2021):3285-3302.