Static-dynamic global graph representation for pedestrian trajectory prediction

doi:10.1016/j.knosys.2023.110775

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Static-dynamic global graph representation for pedestrian trajectory prediction
	Zhou, Hao 1,4; Yang, Xu 4; Fan, Mingyu 2; Huang, Hai 1; Ren, Dongchun 3; Xia, Huaxia 3
刊名	KNOWLEDGE-BASED SYSTEMS
	2023-10-09
卷号	277 页码:13
关键词	Trajectory prediction Social interaction Global graph representation
ISSN号	0950-7051
DOI	10.1016/j.knosys.2023.110775
通讯作者	Fan, Mingyu(fanmingyu@dhu.edu.cn) ; Huang, Hai(haihus@163.com)
英文摘要	Effectively understanding social interactions among pedestrians plays a significant role in accurate pedestrian trajectory prediction. Previous works used either distance-based or data-driven methods to model interactions. However, the distance-based method has difficulty modeling complex interactions and ignores interactive pedestrians that are beyond a certain distance. The data-driven method models interactions among all pedestrians in a scene and introduces noninteractive pedestrians into the model due to the lack of proper supervision. To overcome these limitations, we first propose a novel global graph representation, which considers the spatial distance (from near to far) and the motion state (from static to dynamic), to explicitly model the social interactions among pedestrians. The global graph representation consists of two subgraphs: the static and the dynamic graph representations, where the static graph considers only the nearby pedestrians within a certain distance threshold, and the dynamic graph considers the interactive pedestrians that will likely collide soon. The proposed graph representation explicitly models the interaction by incorporating both the static (location) and dynamic states (velocity) in a distance-based manner. Then, based on the global graph representation, a novel data driven graph encoding network is proposed to extract the interaction features. It adopts two independent LSTMs and an attention module to encode the interaction feature from the perspective of the ego-pedestrian. Finally, the proposed prediction method is evaluated on two benchmark pedestrian trajectory prediction datasets, and comparisons are made with the state-of-the-arts. Experimental results demonstrate the effectiveness of the proposed method.& COPY; 2023 Elsevier B.V. All rights reserved.
资助项目	Beijing Nova Program, China[Z201100006820046] ; National Natural Science Foundation of China[61973301] ; National Natural Science Foundation of China[61972020] ; National Natural Science Foundation of China[61633009] ; National Natural Science Foundation of China[61772373] ; National Natural Science Foundation of China[51579053] ; National Natural Science Foundation of China[U1613213] ; National Key Ramp;D Program of China[2016YFC0300801] ; 13th Five-Year Plan for Equipment Pre-research Fund ; Key Basic Research Project of Shanghai Science and Technology Innovation Plan ; Beijing Science and Technology Project ; Meituan Open Ramp;D Fund ; [2017YFB1300202] ; [61403120301] ; [15JC1403300] ; [Z181100008918018]
WOS关键词	BEHAVIOR ; MODEL
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:001048520100001
资助机构	Beijing Nova Program, China ; National Natural Science Foundation of China ; National Key Ramp;D Program of China ; 13th Five-Year Plan for Equipment Pre-research Fund ; Key Basic Research Project of Shanghai Science and Technology Innovation Plan ; Beijing Science and Technology Project ; Meituan Open Ramp;D Fund
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54014]
专题	多模态人工智能系统全国重点实验室
通讯作者	Fan, Mingyu; Huang, Hai
作者单位	1.Harbin Engn Univ, Coll Shipbldg Engn, Harbin 150001, Peoples R China 2.Donghua Univ, Inst Artificial Intelligence, Shanghai 200051, Peoples R China 3.Intelligent Transportat Div, Beijing 100102, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Hao,Yang, Xu,Fan, Mingyu,et al. Static-dynamic global graph representation for pedestrian trajectory prediction[J]. KNOWLEDGE-BASED SYSTEMS,2023,277:13.
APA	Zhou, Hao,Yang, Xu,Fan, Mingyu,Huang, Hai,Ren, Dongchun,&Xia, Huaxia.(2023).Static-dynamic global graph representation for pedestrian trajectory prediction.KNOWLEDGE-BASED SYSTEMS,277,13.
MLA	Zhou, Hao,et al."Static-dynamic global graph representation for pedestrian trajectory prediction".KNOWLEDGE-BASED SYSTEMS 277(2023):13.