MC-HOG Correlation Tracking with Saliency Proposal
Zhu, Guibo4; Wang, Jinqiao4; Wu, Yi5; Zhang, Xiaoyu6; Lu, Hanqing4; Jinqiao Wang
2016
会议名称The Tirtieth AAAi Conference on Artificial Intelligence
会议录名称In Proceedings of The Thirtieth AAAI Conference on Artificial Intelligence
会议日期February 12-17
会议地点Phoenix, Arizona USA
摘要Designing 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.
 
关键词Visual Tracking Saliency Proposals Mc-hog
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11757
专题模式识别国家重点实验室_图像与视频分析
通讯作者Jinqiao Wang
作者单位1.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
推荐引用方式
GB/T 7714
Zhu, Guibo,Wang, Jinqiao,Wu, Yi,et al. MC-HOG Correlation Tracking with Saliency Proposal[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
MC-HOG Correlation T(596KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhu, Guibo]的文章
[Wang, Jinqiao]的文章
[Wu, Yi]的文章
百度学术
百度学术中相似的文章
[Zhu, Guibo]的文章
[Wang, Jinqiao]的文章
[Wu, Yi]的文章
必应学术
必应学术中相似的文章
[Zhu, Guibo]的文章
[Wang, Jinqiao]的文章
[Wu, Yi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: MC-HOG Correlation Tracking with Saliency Proposal
格式: Unknown
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。