A novel layered object tracking algorithm for forward-looking infrared imagery based on mean shift and feature matching

A novel layered object tracking algorithm for FLIR imagery is proposed based on mean shift algorithm and feature matching. First, infrared object is modeled by kernel histogram. Bhattacharyya coefficient is used to measure the similarity between object model and candidate model. The object is then localized by mean shift algorithm rapidly and efficiently. Because of the low contrast between infrared object and background, low dynamic range of gray level, however, the mean shift tracking results may bring some errors. So, feature matching is employed to eliminate the tracking errors. Feature points are extracted in template object and candidate area by Harris detector. Finally, the accurate localization of infrared object is realized by matching the feature points with the measurement of improved Hausdorff distance. Experiment results verify the effectives and robustness of this tracking algorithm which can improve the tracking performance efficiently.