A unified online dictionary learning framwork with label information for robust object tracking
文献类型：会议论文
| 作者 | Fan BJ(范保杰) ; Sun J(孙静); Cong Y(丛杨); Du YK(杜英魁)
|
| 出版日期 | 2014 |
| 会议名称 | 22nd International Conference on Pattern Recognition, ICPR 2014 |
| 会议日期 | August 24-28, 2014 |
| 会议地点 | Stockholm, Sweden |
| 关键词 | Label information the unified objective function for online dictionary learning optimal linear multi-classifier |
| 页码 | 2311-2316 |
| 中文摘要 | In this paper, a supervised approach to online learn a structured sparse and discriminative representation for object tracking is presented. Label information from training data is incorporated into the dictionary learning process to construct a robust and discriminative dictionary. This is accomplished by adding an ideal-code regularization term and classification error term to the unified objective function. By minimizing the unified objective function we learn the high quality dictionary and optimal linear multi-classifier jointly. Combined with robust sparse coding, the learned classifier is employed directly to separate the object from background. As the tracking continues, the proposed algorithm alternates between robust sparse coding and dictionary updating. Experimental evaluations on the challenging sequences show that the proposed algorithm performs favorably against state-of-the-art methods in terms of effectiveness, accuracy and robustness. |
| 收录类别 | EI ; CPCI（ISTP） |
| 产权排序 | 2 |
| 会议录 | Proceedings; International Conference on Pattern Recognition
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | Piscataway, NJ |
| 语种 | 英语 |
| ISSN号 | 1051-4651 |
| ISBN号 | 978-1-4799-5208-3 |
| WOS记录号 | WOS:000359818002072 |
| 源URL | [http://ir.sia.cn/handle/173321/15611]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 推荐引用方式 GB/T 7714 | Fan BJ,Sun J,Cong Y,et al. A unified online dictionary learning framwork with label information for robust object tracking[C]. 见:22nd International Conference on Pattern Recognition, ICPR 2014. Stockholm, Sweden. August 24-28, 2014. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
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。