Bearing-only target tracking with improved particle filter
Yuejin Lin, Fasheng Wang, Han Yu, Quan Guo · 2010
In this paper, we propose an improved particle filter, and apply this new algorithm to bearing-only tracking problems. The generic particle filter (also called bootstrap filter) suffers a main drawback of not incorporating the latest observations, which is the problem we mainly focus on. An improving scheme is presented to handle this problem, and the underlying idea of the new algorithm is that, at time k, each particle is updated using Kalman filtering equations. Through this update process, the algorithm incorporates the coming observations. In the experiment, we use a bearing-only tracking model to evaluate the performance of the proposed algorithm. The experimental results show its superiority to the generic particle filter.