Improved particle filtering algorithm for maneuvering object tracking using deformation detection

Abstract

In this paper, a new approach is proposed for tracking maneuvering target by improving the basic SIR algorithm. We proposed a dynamic model for maneuvering target. If changes of target model are larger than a predetermined threshold, then the target model will be updated. Practical results show that our proposed approach considerably improves accurate tracking of a maneuvering object. We will compare our proposed approach with the basic SIR algorithm in tracking a single maneuvering aircraft. Results of our proposed algorithm are also illustrated in tracking different maneuvering targets on few real-world case study videos.