Underwater target tracking based on particle filter

摘要

Swimming pool is a dynamic scene with great changes. It is affected by bubbles, light intensity, wave and other factors. In this paper, a new algorithm of underwater moving target tracking is proposed. At first, building the moving target model in underwater video based on RGB histogram. Then particle filter algorithm is adopted to track moving target in view of the complex features of the swimming pool environment. Besides, updating the template adaptively in tracking in order to adapt to target's deformation and external disturbances. Simulation results show that the algorithm proposed in this paper achieves real-time and stable target tracking in the complex surroundings of swimming pool.