Discriminative Correlation Filter with Channel and Spatial Reliability

TL;DR

This paper introduces CSR-DCF, a novel discriminative correlation filter method that incorporates channel and spatial reliability, improving tracking accuracy and robustness for non-rectangular objects in real-time.

Contribution

It proposes a new learning algorithm integrating channel and spatial reliability into DCF tracking, enhancing performance and adaptability.

Findings

Achieves state-of-the-art results on VOT 2016, VOT 2015, and OTB100 datasets.

Runs in real-time on CPU with only two standard features.

Improves tracking of non-rectangular objects and enlarges search region.

Abstract

Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance. We introduce the channel and spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process. The spatial reliability map adjusts the filter 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 reflect channel-wise quality of the learned filters and are used as feature weighting coefficients in localization. Experimentally, with only two simple standard features, HoGs and Colornames, the novel CSR-DCF 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.