Adaptive Correlation Filter Tracking with Weighted Foreground Representation

In recent years, the correlation filter based algorithms show impressive performance for visual tracking. However, the object representations (i.e., feature descriptors) are still not robust. In addition, the models in existing correlation filter based algorithms may be updated by using corrupted samples when the tracking targets are occluded, thus leading to the drifting problem. In this paper, we present a weighted foreground appearance feature descriptor which effectively characterizes the appearance of objects. Moreover, we propose an adaptive model updating strategy to mitigate the problem that the models are updated by using corrupted samples. Our works are based on a recently proposed correlation filter based algorithm, i.e., Staple. By effectively combining the proposed feature descriptor with the adaptively updated Staple framework, the proposed algorithm is highly robust and it can achieve promising performance under complex conditions, such as deformation, rotation and scale variation. Experimental results on the OTB-50 and OTB-100 datasets demonstrate the effectiveness of the proposed tracking algorithm, compared with several other state-of-the-art algorithms.