Dim Target Tracking Base on GM-PHD Filter

In this paper, a real time method for detecting and tracking multiple dim targets in deep space background is presented. We matched the stars in tow continuous images to get their speed at first and found moving targets through speed in both images. Using the targets in the common frame data association is achieved. The Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter is used to track targets to solve the problem of targets disappearance. To initialize of the birth random finite sets (RFSs) the targets sequences are built to find new targets. Extensive experiments on real images sequences show that the proposed approach could effectively meet the requirements of the real-time detection with a low false alarm rate and a high detection probability.