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

• Published in: Ocean engineering Vol. 266; p. 112208
• Main Authors: Yang, Yipu, Yang, Fan, Sun, Liguo, Xiang, Ti, Lv, Pin
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.12.2022
• Subjects: Automatic identification system (AIS); Graph matching; Graph neural network; Optimal transport; Radar track association; Radar track association; Automatic identification system (AIS); Optimal transport; Graph neural network; Graph matching
• DOI: 10.1016/j.oceaneng.2022.112208
• ISSN: 0029-8018

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. •An end-to-end deep network pipeline based on graph matching is proposed.•Time-series data of tracks are transformed into distribution features in the graph.•Graph neural network with self-cross attention distinguishes different tracks.•AIS and radar tracks association is formulated as an optimal transport problem.•Dataset about multi-target track association is available for end-to-end training.