Multi-Spill Surface Target Tracking Based on Oil Particle-Random Point Pattern

In complex marine environments, it is difficult to obtain important parameters such as the number, location, and shape of oil spill surfaces; multiple oil spill surfaces may overlap and merge, which makes the accurate tracking of multiple oil spill surfaces even more difficult. To address the aforementioned issues, proposed a multi-spill surface target tracking method based on the oil particle-random point pattern. Firstly, the oil spill surface is represented by an oil particle model. Then, a random point pattern algorithm is introduced to cluster the oil spill surface. Finally, the GLMB filtering method is utilized to track the centroid trajectory of the oil spill surface, and its shape and concentration information is recorded at the same time. Simulation experiments show the effectiveness of the proposed algorithm.