On the Relations of Correlation Filter Based Trackers and Struck

TL;DR

This paper explores the theoretical relationships between correlation filter based trackers and Struck, revealing their connections and differences through mathematical proofs and extensive experiments on benchmark datasets.

Contribution

It establishes formal relations between SRDCF, CFLB, and Struck, providing new insights into their similarities and differences in visual tracking.

Findings

Proves the relation between SRDCF and CFLB with spatial regularization replaced by a masking matrix.

Shows the asymptotic relation between SRDCF and Struck under specific conditions.

Validates theoretical results with experiments on OTB50 and OTB100 datasets.

Abstract

In recent years, two types of trackers, namely correlation filter based tracker (CF tracker) and structured output tracker (Struck), have exhibited the state-of-the-art performance. However, there seems to be lack of analytic work on their relations in the computer vision community. In this paper, we investigate two state-of-the-art CF trackers, i.e., spatial regularization discriminative correlation filter (SRDCF) and correlation filter with limited boundaries (CFLB), and Struck, and reveal their relations. Specifically, after extending the CFLB to its multiple channel version we prove the relation between SRDCF and CFLB on the condition that the spatial regularization factor of SRDCF is replaced by the masking matrix of CFLB. We also prove the asymptotical approximate relation between SRDCF and Struck on the conditions that the spatial regularization factor of SRDCF is replaced by an indicator function of object bounding box, the weights of SRDCF in its loss item are replaced by those of Struck, the linear kernel is employed by Struck, and the search region tends to infinity. Extensive experiments on public benchmarks OTB50 and OTB100 are conducted to verify our theoretical results. Moreover, we explain how detailed differences among SRDCF, CFLB, and Struck would give rise to slightly different performances on visual sequences