Knowledge Commons of Institute of Automation,CAS
Distractor-aware discrimination learning for online multiple object tracking | |
Zhou, Zongwei1,2; Luo, Wenhan3; Wang, Qiang1,2; Xing, Junliang1,2; Hu, Weiming4,5 | |
发表期刊 | PATTERN RECOGNITION |
ISSN | 0031-3203 |
2020-11-01 | |
期号 | 107页码:10 |
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. |
关键词 | Multi-object tracking Distractor-aware discrimination learning Relational attention learning |
DOI | 10.1016/j.patcog.2020.107512 |
收录类别 | SCI |
语种 | 英语 |
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] |
项目资助者 | 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 |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000552866000053 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40272 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
通讯作者 | Xing, Junliang |
作者单位 | 1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Tencent Lab, Shanghai, Peoples R China 4.Chinese Acad Sci, CAS Ctr Excellence Brian Sci & Intelligence Techn, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
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. |
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 | ||
PR2020_Distractor-aw(840KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论