Amplitude-Aided CPHD Filter for Multitarget Tracking in Infrared Images

The cardinalized probability hypothesis density (CPHD) filter is a powerful tool for multitarget tracking (MTT). However, conventional CPHD filter discriminates targets from clutter only via the motion information, which is not reasonable in the situation of dense clutter. In the tracking, the amplitude of target returns is usually stronger than those coming from clutter, so the amplitude information can be used to enhance the discrimination between targets and clutter. Based on this idea, this paper proposes an amplitude-aided CPHD filter for the MTT in distant infrared (IR) surveillance. First, we model the amplitude of targets and clutter in IR scenarios respectively. For distant IR scenarios, the point spread function (PSF) is used to model the imaging of the point target. The center intensity of the PSF is unknown in practice, and the maximum likelihood estimation (MLE) method is adopted to estimate the target center intensity via the intensities of the latest target detections. Then a likelihood function for MTT is established, and using this likelihood function, a new CPHD recursion is derived, which can distinguish different targets and clutter by the correspondence weight. In the implementation, we adopt the Gaussian mixture (GM) approach to implement the amplitude-aided CPHD filter to achieve efficient performance. In numerical experiments, the results show that the proposed method attains a significant improvement in performance over that only using location measurements.