Learning spatio-temporal correlation filter for visual tracking

Abstract

Correlation filter (CF) trackers have performed impressive performance with high frame rates. However, the limited information in both spatial and temporal domains is only used in the learning of correlation filters, which might limit the tracking performance. To handle this problem, we propose a novel spatio-temporal correlation filter approach, which employs both spatial and temporal cues in the learning, for visual tracking. In particular, we explore the spatial contexts from background whose contents are ambiguous to the target and integrate them into the correlation filter model for more discriminative learning. Moreover, to capture the appearance variations in temporal domain, we also compute a set of target templates and incorporate them into our model. At the same time, the solution of the proposed spatio-temporal correlation filter is closed-form and the tracking efficiency is thus guaranteed. Experimental experiments on benchmark datasets demonstrate the effectiveness of the proposed tracker against several CF ones.