A Robust Parallel Object Tracking Method for Illumination Variations

Illumination variation often occurs in visual tracking, which has a severe impact on the system performance. Many trackers based on Discriminative correlation filter (DCF) have recently obtained promising performance, showing robustness to illumination variation. However, when the target objects undergo significant appearance variation due to intense illumination variation, the features extracted from the object will not have the ability to be discriminated from the background, which causes the tracking algorithm to lose the target in the scene. In this paper, in order to improve the accuracy and robustness of the Discriminative correlation filter (DCF) trackers under intense illumination variation, we propose a very effective strategy by performing multiple region detection and using alternate templates (MRAT). Based on parallel computation, we are able to perform simultaneous detection of multiple regions, equivalently enlarging the search region. Meanwhile the alternate template is saved by a template update mechanism in order to improve the accuracy of the tracker under strong illumination variation. Experimental results on large-scale public benchmark datasets show the effectiveness of the proposed method compared to state-of-the-art methods