CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
MC-HOG Correlation Tracking with Saliency Proposal
Zhu, Guibo4; Wang, Jinqiao4; Wu, Yi5; Zhang, Xiaoyu6; Lu, Hanqing4; Jinqiao Wang
2016
Conference NameThe Tirtieth AAAi Conference on Artificial Intelligence
Source PublicationIn Proceedings of The Thirtieth AAAI Conference on Artificial Intelligence
Conference DateFebruary 12-17
Conference PlacePhoenix, Arizona USA
AbstractDesigning effective feature and handling the model drift problem are two important aspects for online visual tracking. For feature representation, gradient and color features are most widely used, but how to effectively combine them for visual tracking is still an open problem. In this paper, we propose a rich feature descriptor, MC-HOG, by leveraging rich gradient information across multiple color channels or spaces. Then MC-HOG features are embedded into the correlation tracking framework to estimate the state of the target. For handling the model drift problem caused by occlusion or distracter, we propose saliency proposals as prior information to provide candidates and reduce background interference. In addition to saliency proposals, a ranking strategy is proposed to determine the importance of these proposals by exploiting the learnt appearance filter, historical preserved object samples and the distracting proposals. In this way, the proposed approach could effectively explore the color-gradient characteristics and alleviate the model drift problem. Extensive evaluations performed on the benchmark dataset show the superiority of the proposed method.
 
KeywordVisual Tracking Saliency Proposals Mc-hog
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11757
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorJinqiao Wang
Affiliation1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
2.B-DAT & CICAEET, School of Information & Control, Nanjing University of Information Science and Technology, Nanjing, 210044, Jiangsu, China
3.Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100093, China
4.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
5.B-DAT & CICAEET, School of Information & Control, Nanjing University of Information Science and Technology, Nanjing, 210044, Jiangsu, China
6.Institute of Information Engineering, Chinese Academy of Sciences, Beijing, 100093, China
Recommended Citation
GB/T 7714
Zhu, Guibo,Wang, Jinqiao,Wu, Yi,et al. MC-HOG Correlation Tracking with Saliency Proposal[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
MC-HOG Correlation T(596KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhu, Guibo]'s Articles
[Wang, Jinqiao]'s Articles
[Wu, Yi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu, Guibo]'s Articles
[Wang, Jinqiao]'s Articles
[Wu, Yi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu, Guibo]'s Articles
[Wang, Jinqiao]'s Articles
[Wu, Yi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: MC-HOG Correlation Tracking with Saliency Proposal
Format: Unknown
This file does not support browsing at this time
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.