中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Robust Tracking With Discriminative Ranking Lists

文献类型:期刊论文

作者Tang, Ming1; Peng, Xi2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2012-07-01
卷号21期号:7页码:3273-3281
关键词Background model double-scale patch object tracking ranking list
英文摘要In this paper, we propose a novel tracking algorithm, i.e., the discriminative ranking list-based tracker (DRLTracker). The DRL Tracker models the target object and its local background by using ranking lists of patches of different scales within object bounding boxes. The ranking list of each of such patches is its nearest neighbors. Patches of the same scale with ranking lists of high purity values (meaning high probabilities to be on the target object) and some confusable background patches constitute the object model under that scale. A pair of object models of two different scales collaborate to determine which patches may belong to the target object in the next frame. The DRLTracker can effectively alleviate the distraction problem, and its superior ability over several representative and state-of-the-art trackers is demonstrated through extensive experiments.
WOS标题词Science & Technology ; Technology
类目[WOS]Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
研究领域[WOS]Computer Science ; Engineering
关键词[WOS]VISUAL TRACKING ; FRAMEWORK ; OBJECT
收录类别SCI
语种英语
WOS记录号WOS:000305577600014
源URL[http://ir.ia.ac.cn/handle/173211/2980]  
专题自动化研究所_模式识别国家重点实验室_机器人视觉团队
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Tang, Ming,Peng, Xi. Robust Tracking With Discriminative Ranking Lists[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2012,21(7):3273-3281.
APA Tang, Ming,&Peng, Xi.(2012).Robust Tracking With Discriminative Ranking Lists.IEEE TRANSACTIONS ON IMAGE PROCESSING,21(7),3273-3281.
MLA Tang, Ming,et al."Robust Tracking With Discriminative Ranking Lists".IEEE TRANSACTIONS ON IMAGE PROCESSING 21.7(2012):3273-3281.

入库方式: OAI收割

来源: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。