Multi-target association algorithm of AIS-radar tracks using graph matching-based deep neural network

doi:10.1016/j.oceaneng.2022.112208

	Multi-target association algorithm of AIS-radar tracks using graph matching-based deep neural network
	Yang, Yipu 1,2; Yang, Fan 2; Sun, Liguo 1; Xiang, Ti 1,3; Lv, Pin 1
刊名	OCEAN ENGINEERING
	2022-12-15
卷号	266 页码:13
关键词	Automatic identification system (AIS) Radar track association Graph matching Graph neural network Optimal transport
ISSN号	0029-8018
DOI	10.1016/j.oceaneng.2022.112208
通讯作者	Yang, Fan(yangfan@hebut.edu.cn)
英文摘要	Automatic Identification System(AIS) and radar track association is a challenging subject in dense scenes in which there are some undesirable factors, such as multiple targets, complicated target movement patterns, and asynchronous track information, causing inaccurate and inefficient track correlation. Therefore, this research focuses on the optimization problem of AIS and radar track association in dense scenes. Time-series data of tracks are transformed into the distribution features in a graph, which is free from the close dependence of the traditional algorithm on the pre-processing of the time alignment. To this end, an end-to-end deep network pipeline based on graph matching is proposed to overcome the influence of the above factors. It involves a multiscale point-level feature extractor to embed local features. Meanwhile, we devise a cluster-level graph neural network(GNN) with self-cross attention, which can look for global cues that help us disambiguate the correct correlation from complex tracks. Graph matching is estimated by tackling a differentiable optimal transport problem, which minimizes the transport cost and then achieves global optimal track association. Experiments show that the proposed method outperforms other approaches and achieves an ideal score(the precision rate and the recall rate are 0.941 and 0.91, respectively) in our built dataset.
资助项目	National Key Research and De-velopment Program of China for Intelligent Robotics Special Project ; Natural Science Foundation of Hebei Province, China ; [2019YFB131202] ; [F2019202364]
WOS研究方向	Engineering ; Oceanography
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:000875764900001
资助机构	National Key Research and De-velopment Program of China for Intelligent Robotics Special Project ; Natural Science Foundation of Hebei Province, China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50499]
专题	融合创新中心
通讯作者	Yang, Fan
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Hebei Univ Technol, Sch Elect & Informat Engn, Tianjin 300400, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100089, Peoples R China
推荐引用方式 GB/T 7714	Yang, Yipu,Yang, Fan,Sun, Liguo,et al. Multi-target association algorithm of AIS-radar tracks using graph matching-based deep neural network[J]. OCEAN ENGINEERING,2022,266:13.
APA	Yang, Yipu,Yang, Fan,Sun, Liguo,Xiang, Ti,&Lv, Pin.(2022).Multi-target association algorithm of AIS-radar tracks using graph matching-based deep neural network.OCEAN ENGINEERING,266,13.
MLA	Yang, Yipu,et al."Multi-target association algorithm of AIS-radar tracks using graph matching-based deep neural network".OCEAN ENGINEERING 266(2022):13.