It is crucial for unmanned surface vessels (USVs) to detect and track surrounding vessels in real time to avoid collisions at sea. However, the harsh maritime environment poses great challenges to multitarget tracking (MTT). In this paper, a novel tracking by detection framework that integrates the multimodel and multicue (M3C) pipeline is proposed, which aims at improving the detection and tracking performance. Regarding the multimodel, we predicted the maneuver probability of a target vessel via the gated recurrent unit (GRU) model with an attention mechanism, and fused their respective outputs as the output of a kinematic filter. We developed a hybrid affinity model based on multi cues, such as the motion, appearance, and attitude of the ego vessel in the data association stage. By using the proposed ship re-identification approach, the tracker had the capability of appearance matching via metric learning. Experimental evaluation of two public maritime datasets showed that our method achieved state-of-the-art performance, not only in identity switches (IDS) but also in frame rates.
In the complex port environment, ship berthing manipulation is one of the most difficult operations. In this study, an algorithm of berthing and maneuvering was designed for a catamaran unmanned surface vehicle (USV), which is used for port patrol and protection. Considering the influence of wind, waves, and currents, the mathematical model of the maneuvering movement for the twin-hull and twin-propeller USV was established. Based on the Visual Studio development platform, the USV’s berthing manipulation simulation software was designed. Through the turning simulation experiment of the catamaran USV under different differential rotation speeds of the twin propellers, the relationship between the ship’s turning radius and the propeller speed difference was obtained. A simulation experiment of decelerating and stopping ships at different speeds was carried out, which can provide a reference for speed control when berthing. A berthing maneuvering algorithm based on ship maneuverability was proposed. USV’s berthing algorithm includes three stages: approach process, turning process, and berthing process. In the approach process, the appropriate approach speed was select according to the rotation angle. In the turning process, the right and left propeller speed differences were select. In the berthing process, the berthing speed was controlled according to the berthing distance. In the port environment, a berthing simulation experiment for catamaran USV was carried out. The simulation results show that based on the berthing and maneuvering algorithm, the efficiency and safety of catamaran USV berthing can be improved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.