Modified labeled particle probability hypothesis density filter for joint multi-target tracking and classification
Yunxiang Li, Huaitie Xiao, Hao Wu, Qiang Fu, Rui Qin Hu · 2015
Unification of the detection, tracking and classification for multiple targets is an object for random finite sets based filters developing. Introduction of target attribute information can improve tracking performance. Then, as the improved labeled particle probability hypothesis density (IL-P-PHD) filter is capable of joint detection and tracking, we will fuse obtained target attribute information into IL-P-PHD filter to propose a joint tracking and classification particle PHD (JTC-P-PHD) algorithm. We are in the expectation that the proposed JTC-P-PHD algorithm is capable of joint detection, tracking as well as classification of multiple targets. Numerical examples demonstrate that the proposed JTC-P-PHD algorithm behaves in a manner consistent with our expectations.