Imperial College London

DrKrystianMikolajczyk

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Reader in Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 6220k.mikolajczyk

 
 
//

Location

 

Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Akin:2016:10.1016/j.jvcir.2016.04.018,
author = {Akin, O and Erdem, E and Erdem, A and Mikolajczyk, K},
doi = {10.1016/j.jvcir.2016.04.018},
journal = {Journal of Visual Communication and Image Representation},
pages = {763--774},
title = {Deformable part-based tracking by coupled global and local correlation filters},
url = {http://dx.doi.org/10.1016/j.jvcir.2016.04.018},
volume = {38},
year = {2016}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Correlation filters have recently attracted attention in visual tracking due to their efficiency and high performance. However, their application to long-term tracking is somewhat limited since these trackers are not equipped with mechanisms to cope with challenging cases like partial occlusion, deformation or scale changes. In this paper, we propose a deformable part-based correlation filter tracking approach which depends on coupled interactions between a global filter and several part filters. Specifically, local filters provide an initial estimate, which is then used by the global filter as a reference to determine the final result. Then, the global filter provides a feedback to the part filters regarding their updates and the related deformation parameters. In this way, our proposed collaborative model handles not only partial occlusion but also scale changes. Experiments on two large public benchmark datasets demonstrate that our approach gives significantly better results compared with the state-of-the-art trackers.
AU - Akin,O
AU - Erdem,E
AU - Erdem,A
AU - Mikolajczyk,K
DO - 10.1016/j.jvcir.2016.04.018
EP - 774
PY - 2016///
SN - 1095-9076
SP - 763
TI - Deformable part-based tracking by coupled global and local correlation filters
T2 - Journal of Visual Communication and Image Representation
UR - http://dx.doi.org/10.1016/j.jvcir.2016.04.018
VL - 38
ER -