Target Tracking Using Particle Filter with X-Band Nautical Radar

In this paper, a particle filter (PF) method is proposed for target tracking based on a practical X-band nautical radar image sequence, using two histogram-based target models: a kernel-weighted histogram model and a background-weighted histogram model. In particular, the sampling importance resampling (SIR) particle filter is implemented to provide a recursively probabilistic estimation procedure for target tracking. For the measurement model of the particle filter, a Bhattacharyya coefficient based similarity function is utilized to compare the reference target and target candidate, which are represented by the histogram of the target area in the radar image. Within the PF tracking procedure, both the kernel-weighted and background-weighted models are applied with estimated target tracks compared with the practical GPS data. The experiment shows that both models can effectively complete the target tracking task with the kernel-weighted model performing better when the reference model is accurately selected, with the background-weighted model being more flexible.