Particle filter re-detection for visual tracking via correlation filters

TL;DR

This paper introduces a particle filter re-detection method combined with correlation filters to improve object localization accuracy in visual tracking, especially in challenging scenes, demonstrating superior performance on standard datasets.

Contribution

The paper proposes a novel particle filter re-detection approach integrated with correlation filters and a new scale evaluation mechanism for enhanced tracking accuracy.

Findings

Outperforms state-of-the-art methods on OTB2013 and OTB2015 datasets.

Effectively handles ambiguous response maps in correlation filter tracking.

Provides more accurate object localization in complex scenes.

Abstract

Most of the correlation filter based tracking algorithms can achieve good performance and maintain fast computational speed. However, in some complicated tracking scenes, there is a fatal defect that causes the object to be located inaccurately. In order to address this problem, we propose a particle filter redetection based tracking approach for accurate object localization. During the tracking process, the kernelized correlation filter (KCF) based tracker locates the object by relying on the maximum response value of the response map; when the response map becomes ambiguous, the KCF tracking result becomes unreliable. Our method can provide more candidates by particle resampling to detect the object accordingly. Additionally, we give a new object scale evaluation mechanism, which merely considers the differences between the maximum response values in consecutive frames. Extensive experiments on OTB2013 and OTB2015 datasets demonstrate that the proposed tracker performs favorably in relation to the state-of-the-art methods.