中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
Distractor-aware discrimination learning for online multiple object tracking

文献类型：期刊论文

作者Zhou, Zongwei1,4; Luo, Wenhan5; Wang, Qiang1,4; Xing, Junliang1,4; Hu, Weiming2,3
刊名PATTERN RECOGNITION
出版日期2020-11-01
卷号107页码:10
关键词Multi-object tracking Distractor-aware discrimination learning Relational attention learning
ISSN号0031-3203
DOI10.1016/j.patcog.2020.107512
通讯作者Xing, Junliang(jlxing@nlpr.ia.ac.cn)
英文摘要Online multi-object tracking needs to overcome the intrinsic detector deficiencies, e.g., missing detections, false alarms, and inaccurate detection responses, to grow multiple object trajectories without using future information. Various distractions exist during this growing process like background clutters, similar targets, and occlusions, which present a great challenge. We in this work propose a method for learning a distractor-aware discriminative model that can handle continuous missed and inaccurate detection problems due to the occlusion or the motion blur. To deal with target appearance variations, a relational attention learning mechanism is proposed to capture the distinctive target appearances by selectively aggregating features from history states with weights extracted from their appearance topological relationship. Based on the discrimination model, a multi-stage tracking pipeline is designed for automatic trajectory initialization, propagation, and termination. Extensive experimental analyses and comparisons demonstrate its state-of-the-art performance on widely used challenging MOT16 and MOT17 benchmarks. The source code of this work is released to facilitate further studies on the multi-object tracking problem. (C) 2020 Elsevier Ltd. All rights reserved.
资助项目National Key R&D Program of China[2018AAA0102802] ; National Key R&D Program of China[2018AAA0102803] ; National Key R&D Program of China[2018AAA0102800] ; NSFC-general technology collaborative Fund for basic research[U1636218] ; Natural Science Foundation of China[61672519] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61721004] ; Beijing Natural Science Foundation[L172051] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC040] ; National Natural Science Foundation of Guangdong[2018B030311046]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000552866000053
出版者ELSEVIER SCI LTD
资助机构National Key R&D Program of China ; NSFC-general technology collaborative Fund for basic research ; Natural Science Foundation of China ; Beijing Natural Science Foundation ; Key Research Program of Frontier Sciences, CAS ; National Natural Science Foundation of Guangdong
源URL[http://ir.ia.ac.cn/handle/173211/40271]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
通讯作者Xing, Junliang
作者单位1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
2.Chinese Acad Sci, CAS Ctr Excellence Brian Sci & Intelligence Techn, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Beijing, Peoples R China
5.Tencent Lab, Shanghai, Peoples R China
推荐引用方式
GB/T 7714		 Zhou, Zongwei,Luo, Wenhan,Wang, Qiang,et al. Distractor-aware discrimination learning for online multiple object tracking[J]. PATTERN RECOGNITION,2020,107:10.
APA Zhou, Zongwei,Luo, Wenhan,Wang, Qiang,Xing, Junliang,&Hu, Weiming.(2020).Distractor-aware discrimination learning for online multiple object tracking.PATTERN RECOGNITION,107,10.
MLA Zhou, Zongwei,et al."Distractor-aware discrimination learning for online multiple object tracking".PATTERN RECOGNITION 107(2020):10.

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。