Correlation filters based on temporal regularization and background awareness,

Abstract

Information about background appearance and previous tracked frames is significant for effectively discriminating a target from a complex scene. In this paper, we propose a novel tracker called temporal regularization and background-aware correlation filter (TRBACF) tracker based on the theory of correlation filter. In the proposed TRBACF tracker, an improved circular shift operation for collecting training samples is used to obtain more background information, which can enhance the discrimination ability of the learned correlation filters. Furthermore, to ensure the long-term tracking performance, a temporal regularization term is added to the appearance model of the classical correlation filter. The developed appearance model can take advantage of the similarity of the filters in the adjacent frames and improve the learned filter to be more adaptive to variations in the scene. Extensive experimental results on various challenging videos demonstrate that the proposed TRBACF tracker achieves superior accuracy than some state-of-the-art trackers.