부산대학교 도서관

With the development of Marine technology, the importance of Marine environment exploration is increasing day by day. Imaging sonar is the most effective means in ocean exploration and forward sonar is one of the most widely used imaging sonar. Due to the complex ocean environment, the underwater target tracking in forward sonar images is easy to be affected by occlusion and deformation, resulting in poor tracking effect. Aiming at the above problems in underwater target tracking, this paper proposes an improved KCF algorithm and applies it to the traditional forward sonar target tracking field. The experimental results show that this method can effectively overcome the influence of occlusion and deformation and achieve high accuracy and computing speed.