University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Learning Low-rank and Sparse Discriminative Correlation Filters for Coarse-to-Fine Visual Object Tracking

Xu, Tianyang, Feng, Zhen-Hua, Wu, Xiao-Jun and Kittler, Josef (2019) Learning Low-rank and Sparse Discriminative Correlation Filters for Coarse-to-Fine Visual Object Tracking IEEE Transactions on Circuits and Systems for Video Technology. pp. 1-13.

[img]
Preview
Text
Learning Low-rank and Sparse Discriminative Correlation Filters.pdf - Accepted version Manuscript

Download (11MB) | Preview

Abstract

Discriminative correlation filter (DCF) has achieved advanced performance in visual object tracking with remarkable efficiency guaranteed by its implementation in the frequency domain. However, the effect of the structural relationship of DCF and object features has not been adequately explored in the context of the filter design. To remedy this deficiency, this paper proposes a Low-rank and Sparse DCF (LSDCF) that improves the relevance of features used by discriminative filters. To be more specific, we extend the classical DCF paradigm from ridge regression to lasso regression, and constrain the estimate to be of low-rank across frames, thus identifying and retaining the informative filters distributed on a low-dimensional manifold. To this end, specific temporal-spatial-channel configurations are adaptively learned to achieve enhanced discrimination and interpretability. In addition, we analyse the complementary characteristics between hand-crafted features and deep features, and propose a coarse-to-fine heuristic tracking strategy to further improve the performance of our LSDCF. Last, the augmented Lagrange multiplier optimisation method is used to achieve efficient optimisation. The experimental results obtained on a number of well-known benchmarking datasets, including OTB2013, OTB50, OTB100, TC128, UAV123, VOT2016 and VOT2018, demonstrate the effectiveness and robustness of the proposed method, delivering outstanding performance compared to the state-of-the-art trackers.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Xu, Tianyangtx0002@surrey.ac.uk
Feng, Zhen-Huaz.feng@surrey.ac.uk
Wu, Xiao-Jun
Kittler, JosefJ.Kittler@surrey.ac.uk
Date : 2 October 2019
Funders : Engineering and Physical Sciences Research Council (EPSRC)
DOI : 10.1109/TCSVT.2019.2945068
Grant Title : FACER2VM
Copyright Disclaimer : © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Uncontrolled Keywords : Visual object tracking; Discriminative correlation filter; Lasso regression; Target tracking; Visualization; Correlation; Object tracking; Neural networks; Task analysis; Feature extraction
Depositing User : Clive Harris
Date Deposited : 25 Oct 2019 08:35
Last Modified : 25 Oct 2019 08:35
URI: http://epubs.surrey.ac.uk/id/eprint/852973

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800