An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest Classifier
The fast compressive tracking (FCT) algorithm is a simple and efficient algorithm, which is proposed in recent years. But, it is difficult to deal with the factors such as occlusion, appearance changes, pose variation, etc in processing. The reasons are that, Firstly, even if the naive Bayes classif...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2016-01-01
|
Series: | MATEC Web of Conferences |
Subjects: | |
Online Access: | http://dx.doi.org/10.1051/matecconf/20165901003 |
id |
doaj-0b63b84f6b4d49b28e9a03b70efb443f |
---|---|
record_format |
Article |
spelling |
doaj-0b63b84f6b4d49b28e9a03b70efb443f2021-02-02T03:28:22ZengEDP SciencesMATEC Web of Conferences2261-236X2016-01-01590100310.1051/matecconf/20165901003matecconf_icfst2016_01003An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest ClassifierXiong JintaoJiang PanYang JianyuZhong ZhibinZou RanZhu BaozhongThe fast compressive tracking (FCT) algorithm is a simple and efficient algorithm, which is proposed in recent years. But, it is difficult to deal with the factors such as occlusion, appearance changes, pose variation, etc in processing. The reasons are that, Firstly, even if the naive Bayes classifier is fast in training, it is not robust concerning the noise. Secondly, the parameters are required to vary with the unique environment for accurate tracking. In this paper, we propose an improved fast compressive tracking algorithm based on online random forest (FCT-ORF) for robust visual tracking. Firstly, we combine ideas with the adaptive compressive sensing theory regarding the weighted random projection to exploit both local and discriminative information of the object. The second reason is the online random forest classifier for online tracking which is demonstrated with more robust to the noise adaptively and high computational efficiency. The experimental results show that the algorithm we have proposed has a better performance in the field of occlusion, appearance changes, and pose variation than the fast compressive tracking algorithm’s contribution.http://dx.doi.org/10.1051/matecconf/20165901003fast compressive trackingnaive Byes classifieronlinerandom forest |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiong Jintao Jiang Pan Yang Jianyu Zhong Zhibin Zou Ran Zhu Baozhong |
spellingShingle |
Xiong Jintao Jiang Pan Yang Jianyu Zhong Zhibin Zou Ran Zhu Baozhong An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest Classifier MATEC Web of Conferences fast compressive tracking naive Byes classifier online random forest |
author_facet |
Xiong Jintao Jiang Pan Yang Jianyu Zhong Zhibin Zou Ran Zhu Baozhong |
author_sort |
Xiong Jintao |
title |
An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest Classifier |
title_short |
An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest Classifier |
title_full |
An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest Classifier |
title_fullStr |
An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest Classifier |
title_full_unstemmed |
An Improved Fast Compressive Tracking Algorithm Based on Online Random Forest Classifier |
title_sort |
improved fast compressive tracking algorithm based on online random forest classifier |
publisher |
EDP Sciences |
series |
MATEC Web of Conferences |
issn |
2261-236X |
publishDate |
2016-01-01 |
description |
The fast compressive tracking (FCT) algorithm is a simple and efficient algorithm, which is proposed in recent years. But, it is difficult to deal with the factors such as occlusion, appearance changes, pose variation, etc in processing. The reasons are that, Firstly, even if the naive Bayes classifier is fast in training, it is not robust concerning the noise. Secondly, the parameters are required to vary with the unique environment for accurate tracking. In this paper, we propose an improved fast compressive tracking algorithm based on online random forest (FCT-ORF) for robust visual tracking. Firstly, we combine ideas with the adaptive compressive sensing theory regarding the weighted random projection to exploit both local and discriminative information of the object. The second reason is the online random forest classifier for online tracking which is demonstrated with more robust to the noise adaptively and high computational efficiency. The experimental results show that the algorithm we have proposed has a better performance in the field of occlusion, appearance changes, and pose variation than the fast compressive tracking algorithm’s contribution. |
topic |
fast compressive tracking naive Byes classifier online random forest |
url |
http://dx.doi.org/10.1051/matecconf/20165901003 |
work_keys_str_mv |
AT xiongjintao animprovedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT jiangpan animprovedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT yangjianyu animprovedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT zhongzhibin animprovedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT zouran animprovedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT zhubaozhong animprovedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT xiongjintao improvedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT jiangpan improvedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT yangjianyu improvedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT zhongzhibin improvedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT zouran improvedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier AT zhubaozhong improvedfastcompressivetrackingalgorithmbasedononlinerandomforestclassifier |
_version_ |
1724307653342003200 |