Robust Visual Tracking With Spatial Regularization Kernelized Correlation Filter Constrained by a Learning Spatial Reliability Map
As a basic research topic in computer vision, visual tracking is still challenging because of the complexity of the tracking problems, such as abrupt motion, out-of-view, deformation, and heavy occlusion. In this paper, we extend the kernelized correlation filter (CF) for robust tracking by introduc...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8654600/ |
id |
doaj-04446fde4d7d486695d141d691f23fbc |
---|---|
record_format |
Article |
spelling |
doaj-04446fde4d7d486695d141d691f23fbc2021-03-29T22:29:07ZengIEEEIEEE Access2169-35362019-01-017273392735110.1109/ACCESS.2019.29022168654600Robust Visual Tracking With Spatial Regularization Kernelized Correlation Filter Constrained by a Learning Spatial Reliability MapQianbo Liu0https://orcid.org/0000-0002-4334-065XGuoqing Hu1Md Mojahidul Islam2https://orcid.org/0000-0002-8408-4939School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, ChinaAs a basic research topic in computer vision, visual tracking is still challenging because of the complexity of the tracking problems, such as abrupt motion, out-of-view, deformation, and heavy occlusion. In this paper, we extend the kernelized correlation filter (CF) for robust tracking by introducing spatial regularization components to penalize the CF coefficients. To afford a more confident prediction, we construct a spatial reliability map based on the color histogram to enforce the detecting samples near the target center. The feature fusion and the model update mechanism are further employed to improve the effectiveness of tracking. The extensive experiments are executed on the OTB-2013, OTB-2015, and Temple Color-128 datasets. The comprehensive results demonstrate the superiority of our proposed method comparing to the representative tracks on these datasets.https://ieeexplore.ieee.org/document/8654600/Feature fusionmodel update mechanismspatial regularization componentsspatial reliability map |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Qianbo Liu Guoqing Hu Md Mojahidul Islam |
spellingShingle |
Qianbo Liu Guoqing Hu Md Mojahidul Islam Robust Visual Tracking With Spatial Regularization Kernelized Correlation Filter Constrained by a Learning Spatial Reliability Map IEEE Access Feature fusion model update mechanism spatial regularization components spatial reliability map |
author_facet |
Qianbo Liu Guoqing Hu Md Mojahidul Islam |
author_sort |
Qianbo Liu |
title |
Robust Visual Tracking With Spatial Regularization Kernelized Correlation Filter Constrained by a Learning Spatial Reliability Map |
title_short |
Robust Visual Tracking With Spatial Regularization Kernelized Correlation Filter Constrained by a Learning Spatial Reliability Map |
title_full |
Robust Visual Tracking With Spatial Regularization Kernelized Correlation Filter Constrained by a Learning Spatial Reliability Map |
title_fullStr |
Robust Visual Tracking With Spatial Regularization Kernelized Correlation Filter Constrained by a Learning Spatial Reliability Map |
title_full_unstemmed |
Robust Visual Tracking With Spatial Regularization Kernelized Correlation Filter Constrained by a Learning Spatial Reliability Map |
title_sort |
robust visual tracking with spatial regularization kernelized correlation filter constrained by a learning spatial reliability map |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
As a basic research topic in computer vision, visual tracking is still challenging because of the complexity of the tracking problems, such as abrupt motion, out-of-view, deformation, and heavy occlusion. In this paper, we extend the kernelized correlation filter (CF) for robust tracking by introducing spatial regularization components to penalize the CF coefficients. To afford a more confident prediction, we construct a spatial reliability map based on the color histogram to enforce the detecting samples near the target center. The feature fusion and the model update mechanism are further employed to improve the effectiveness of tracking. The extensive experiments are executed on the OTB-2013, OTB-2015, and Temple Color-128 datasets. The comprehensive results demonstrate the superiority of our proposed method comparing to the representative tracks on these datasets. |
topic |
Feature fusion model update mechanism spatial regularization components spatial reliability map |
url |
https://ieeexplore.ieee.org/document/8654600/ |
work_keys_str_mv |
AT qianboliu robustvisualtrackingwithspatialregularizationkernelizedcorrelationfilterconstrainedbyalearningspatialreliabilitymap AT guoqinghu robustvisualtrackingwithspatialregularizationkernelizedcorrelationfilterconstrainedbyalearningspatialreliabilitymap AT mdmojahidulislam robustvisualtrackingwithspatialregularizationkernelizedcorrelationfilterconstrainedbyalearningspatialreliabilitymap |
_version_ |
1724191459435872256 |