Abstract
Short-term tracking is an open and challenging problem for which discriminative correlation fifilters (DCF) have shown excellent performance.We introduce the channel and spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its effificient and seamless integration in the fifilter update and the tracking process. The spatial reliability map adjusts the fifilter support to the part of the object suitable for tracking. This both allows to enlarge the search region and improves tracking of non-rectangular objects. Reliability scores reflflect channel-wise quality of the learned fifilters and are used as feature weighting coeffifi- cients in localization. Experimentally, with only two simple standard features, HoGs and Colornames, the novel CSRDCF method – DCF with Channel and Spatial Reliability – achieves state-of-the-art results on VOT 2016, VOT 2015 and OTB100. The CSR-DCF runs in real-time on a CPU.