Robust tracking algorithm for infrared target via correlation filter and particle filter

Abstract

To overcome the shortcomings of low signal-to-noise ratio and less available information of infrared images, as well as the challenges of fast camera motion and partial occlusion, a robust tracker via correlation filter and particle filter is proposed for infrared target. Firstly, to explore the strength of the particle-filter-based tracker, a Lp-norm based low-rank sparse tracker is proposed. Then, a robust tracker is proposed by complementing the advantages of both correlation-filter-based and particle-filter-based trackers, which can not only handle the camera motion challenge, but also improve tracking accuracy and robustness. Finally, to address the tracking drift problem and deal with the partial occlusion challenge, an effective template update approach is designed according to different characteristics of correlation-filter-based and particle-filter-based trackers. Experimental results on the VOT-TIR2015 benchmark set demonstrate that the proposed tracker can not only outperform several state-of-the-art trackers in terms of both accuracy and robustness, but also effectively handle the challenges such as camera motion, partial occlusion, size change and motion change.