A Particle Filter and Fuzzy Clustering Based Algorithm for Tracking Dim Moving Multiple Point Targets in IR Image Sequence

The tracking algorithm described in this paper adopts the fuzzy clustering method to fuse the single frame detection measurements from different tracking windows, then the fused measurements will be inputted to the Particle filters, via the recursive prediction and updating, getting the moving state of each target at each discrete time. The theoretical and experimental results show that the algorithm presented in this paper can keep dynamic stability and robustness while providing good real-time tracking performance.