Robust Visual Tracking with Discrimination Dictionary Learning
It is a challenging issue to deal with kinds of appearance variations in visual tracking. Existing tracking algorithms build appearance models upon target templates. Those models are not robust to significant appearance variations due to factors such as illumination variations, partial occlusions, a...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2018-01-01
|
Series: | Advances in Multimedia |
Online Access: | http://dx.doi.org/10.1155/2018/7357284 |
id |
doaj-21ce19e10bf84053b7446c58e0d5bf8b |
---|---|
record_format |
Article |
spelling |
doaj-21ce19e10bf84053b7446c58e0d5bf8b2020-11-25T01:33:50ZengHindawi LimitedAdvances in Multimedia1687-56801687-56992018-01-01201810.1155/2018/73572847357284Robust Visual Tracking with Discrimination Dictionary LearningYuanyun Wang0Chengzhi Deng1Jun Wang2Wei Tian3Shengqian Wang4Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing, Nanchang Institute of Technology, Nanchang 330099, ChinaJiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing, Nanchang Institute of Technology, Nanchang 330099, ChinaJiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing, Nanchang Institute of Technology, Nanchang 330099, ChinaJiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing, Nanchang Institute of Technology, Nanchang 330099, ChinaJiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing, Nanchang Institute of Technology, Nanchang 330099, ChinaIt is a challenging issue to deal with kinds of appearance variations in visual tracking. Existing tracking algorithms build appearance models upon target templates. Those models are not robust to significant appearance variations due to factors such as illumination variations, partial occlusions, and scale variation. In this paper, we propose a robust tracking algorithm with a learnt dictionary to represent target candidates. With the learnt dictionary, a target candidate is represented with a linear combination of dictionary atoms. The discriminative information in learning samples is exploited. In the meantime, the learning processing of dictionaries can learn appearance variations. Based on the learnt dictionary, we can get a more stable representation for target candidates. Additionally, the observation likelihood is evaluated based on both the reconstruct error and dictionary coefficients with l1 constraint. Comprehensive experiments demonstrate the superiority of the proposed tracking algorithm to some state-of-the-art tracking algorithms.http://dx.doi.org/10.1155/2018/7357284 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yuanyun Wang Chengzhi Deng Jun Wang Wei Tian Shengqian Wang |
spellingShingle |
Yuanyun Wang Chengzhi Deng Jun Wang Wei Tian Shengqian Wang Robust Visual Tracking with Discrimination Dictionary Learning Advances in Multimedia |
author_facet |
Yuanyun Wang Chengzhi Deng Jun Wang Wei Tian Shengqian Wang |
author_sort |
Yuanyun Wang |
title |
Robust Visual Tracking with Discrimination Dictionary Learning |
title_short |
Robust Visual Tracking with Discrimination Dictionary Learning |
title_full |
Robust Visual Tracking with Discrimination Dictionary Learning |
title_fullStr |
Robust Visual Tracking with Discrimination Dictionary Learning |
title_full_unstemmed |
Robust Visual Tracking with Discrimination Dictionary Learning |
title_sort |
robust visual tracking with discrimination dictionary learning |
publisher |
Hindawi Limited |
series |
Advances in Multimedia |
issn |
1687-5680 1687-5699 |
publishDate |
2018-01-01 |
description |
It is a challenging issue to deal with kinds of appearance variations in visual tracking. Existing tracking algorithms build appearance models upon target templates. Those models are not robust to significant appearance variations due to factors such as illumination variations, partial occlusions, and scale variation. In this paper, we propose a robust tracking algorithm with a learnt dictionary to represent target candidates. With the learnt dictionary, a target candidate is represented with a linear combination of dictionary atoms. The discriminative information in learning samples is exploited. In the meantime, the learning processing of dictionaries can learn appearance variations. Based on the learnt dictionary, we can get a more stable representation for target candidates. Additionally, the observation likelihood is evaluated based on both the reconstruct error and dictionary coefficients with l1 constraint. Comprehensive experiments demonstrate the superiority of the proposed tracking algorithm to some state-of-the-art tracking algorithms. |
url |
http://dx.doi.org/10.1155/2018/7357284 |
work_keys_str_mv |
AT yuanyunwang robustvisualtrackingwithdiscriminationdictionarylearning AT chengzhideng robustvisualtrackingwithdiscriminationdictionarylearning AT junwang robustvisualtrackingwithdiscriminationdictionarylearning AT weitian robustvisualtrackingwithdiscriminationdictionarylearning AT shengqianwang robustvisualtrackingwithdiscriminationdictionarylearning |
_version_ |
1725075428389945344 |