An improvement on GM-PHD filter for target tracking in presence of subsequent miss-detection

Gaussian mixture probability hypothesis density (GM-PHD) filter is proposed as a closed form solution of PHD filter to estimate the first-order moment of the multi-target posterior density. Recently, different methods such as Competitive GM-PHD (CGM-PHD), Penalized GM-PHD (PGM-PHD) and Collaborative PGM-PHD (CPGM-PHD) are proposed to enhance the performance of GM-PHD filter for tracking closely spaced targets. These methods have no assumption about possible subsequent missed detections which occur in some practical applications. For this reason, the performance of these filters degrades in this condition. In this paper, we propose a novel improvement on GM-PHD filter to track targets in possible subsequent missed detections. In addition to targets weight, we define a probability of confirm (PC) for each target which is adaptively calculated in time. We also propose a new state refinement and state extraction methods based on the defined PC. The experimental results provided for different uncertainties show the effectiveness of the proposed method.