CASIA OpenIR  > 融合创新中心
Multi-target association algorithm of AIS-radar tracks using graph matching-based deep neural network
Yang, Yipu1,2; Yang, Fan1; Sun, Liguo2; Xiang, Ti2,3; Lv, Pin2
Source PublicationOCEAN ENGINEERING
ISSN0029-8018
2022-12-15
Volume266Pages:13
Corresponding AuthorYang, Fan(yangfan@hebut.edu.cn)
AbstractAutomatic 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.
KeywordAutomatic identification system (AIS) Radar track association Graph matching Graph neural network Optimal transport
DOI10.1016/j.oceaneng.2022.112208
Indexed BySCI
Language英语
Funding ProjectNational Key Research and De-velopment Program of China for Intelligent Robotics Special Project ; Natural Science Foundation of Hebei Province, China ; [2019YFB131202] ; [F2019202364]
Funding OrganizationNational Key Research and De-velopment Program of China for Intelligent Robotics Special Project ; Natural Science Foundation of Hebei Province, China
WOS Research AreaEngineering ; Oceanography
WOS SubjectEngineering, Marine ; Engineering, Civil ; Engineering, Ocean ; Oceanography
WOS IDWOS:000875764900001
PublisherPERGAMON-ELSEVIER SCIENCE LTD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/50500
Collection融合创新中心
Corresponding AuthorYang, Fan
Affiliation1.Hebei Univ Technol, Sch Elect & Informat Engn, Tianjin 300400, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100089, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
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.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, Yipu]'s Articles
[Yang, Fan]'s Articles
[Sun, Liguo]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, Yipu]'s Articles
[Yang, Fan]'s Articles
[Sun, Liguo]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, Yipu]'s Articles
[Yang, Fan]'s Articles
[Sun, Liguo]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.