DTDNet: Dynamic Target Driven Network for pedestrian trajectory prediction

doi:10.3389/fnins.2024.1346374

	DTDNet: Dynamic Target Driven Network for pedestrian trajectory prediction
	Liu, Shaohua 1; Sun, Jingkai 1,2; Yao, Pengfei 2,3; Zhu, Yinglong 1,2; Mao, Tianlu 2; Wang, Zhaoqi 2
	2024-04-30
发表期刊	FRONTIERS IN NEUROSCIENCE
卷号	18 页码:11
摘要	Predicting the trajectories of pedestrians is an important and difficult task for many applications, such as robot navigation and autonomous driving. Most of the existing methods believe that an accurate prediction of the pedestrian intention can improve the prediction quality. These works tend to predict a fixed destination coordinate as the agent intention and predict the future trajectory accordingly. However, in the process of moving, the intention of a pedestrian could be a definite location or a general direction and area, and may change dynamically with the changes of surrounding. Thus, regarding the agent intention as a fixed 2-d coordinate is insufficient to improve the future trajectory prediction. To address this problem, we propose Dynamic Target Driven Network for pedestrian trajectory prediction (DTDNet), which employs a multi-precision pedestrian intention analysis module to capture this dynamic. To ensure that this extracted feature contains comprehensive intention information, we design three sub-tasks: predicting coarse-precision endpoint coordinate, predicting fine-precision endpoint coordinate and scoring scene sub-regions. In addition, we propose a original multi-precision trajectory data extraction method to achieve multi-resolution representation of future intention and make it easier to extract local scene information. We compare our model with previous methods on two publicly available datasets (ETH-UCY and Stanford Drone Dataset). The experimental results show that our DTDNet achieves better trajectory prediction performance, and conducts better pedestrian intention feature representation.
关键词	multimodal trajectory prediction pedestrian intention prediction multi-precision motion prediction multi-task neural network trajectory endpoint prediction
DOI	10.3389/fnins.2024.1346374
收录类别	SCI
语种	英语
资助项目	Major Program of National Natural Science Foundation of China[91938301] ; National Key Research and Development Program of China[2020YFB1710400] ; Youth Program of National Natural Science Foundation of China[62002345] ; Innovation Program of Institute of Computing Technology Chinese Academy of Sciences[E261070]
WOS研究方向	Neurosciences & Neurology
WOS类目	Neurosciences
WOS记录号	WOS:001220613800001
出版者	FRONTIERS MEDIA SA
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38969
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Mao, Tianlu
作者单位	1.Beijing Univ Posts & Telecommun, Sch Elect Engn, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Shaohua,Sun, Jingkai,Yao, Pengfei,et al. DTDNet: Dynamic Target Driven Network for pedestrian trajectory prediction[J]. FRONTIERS IN NEUROSCIENCE,2024,18:11.
APA	Liu, Shaohua,Sun, Jingkai,Yao, Pengfei,Zhu, Yinglong,Mao, Tianlu,&Wang, Zhaoqi.(2024).DTDNet: Dynamic Target Driven Network for pedestrian trajectory prediction.FRONTIERS IN NEUROSCIENCE,18,11.
MLA	Liu, Shaohua,et al."DTDNet: Dynamic Target Driven Network for pedestrian trajectory prediction".FRONTIERS IN NEUROSCIENCE 18(2024):11.