RGBT Dual-modal Tracking with Weighted Discriminative Correlation Filters

Compared with single-modal RGB trackers, dual-modal RGBT(RGB-Thermal) trackers are more robust to illumination variation. In real scenarios, however, dual-modal trackers are severely influenced by partial occlusion and shape deformation. To tackle above problems, in this paper, we propose a weighted DCF(Discriminative Correlation Filter) based RGBT tracker. This tracker derives a weight map from a RGBT image pair and guides correlation filter training with this map. The occlusion state of the foreground target is inferred from the weight map. Experimental results on the public RGBT234 dataset demonstrate that our tracker is able to cope well with partial occlusion and shape deformation and achieves robust and persistent tracking in complex scenarios.