Grid Map Assisted Radar Target Tracking in a Detection Occluded Maritime Environment

In unmanned surface vehicle (USV) platform-based marine radar target detection, as a result of low radar installation height, the presence of target occlusion by islands, nearby vessels as well as near-shore infrastructure is very common. This makes it difficult for a ship target to be consistently detected and tracked, leading to potential track loss and collision risks. However, efficient solutions for identifying occlusion and maintaining sound tracking performance in a detection occluded maritime environment are not well explored in the literature. In this article, an event-driven occupancy grid-assisted anti-occlusion approach is proposed. When the event of target missed detection occurs, the proposed algorithm utilizes available information from an electronic navigation chart (ENC), automatic identification system (AIS) as well as marine radar to build an occupancy grid map for reasoning whether the radar signal is blocked by any existing objects lying in between of the target and the USV. An occlusion adaptive target tracking framework is thus constructed to improve the stability of the target tracking. Both the simulation and real-data validation results show that the proposed algorithm is able to improve the target tracking performance in a detection occlusion environment.