Knowledge Commons of Institute of Automation,CAS
Domain Adaptation Tracker with Global and Local Searching | |
Zhao, Fei1,2![]() ![]() ![]() ![]() | |
发表期刊 | IEEE Access
![]() |
ISSN | 2169-3536 |
2018 | |
期号 | 6页码:42997 - 43008 |
摘要 | For the convolutional neural network (CNN)-based trackers, most of them locate the target only within a local area, which makes the trackers hard to recapture the target after drifting into the background. Besides, most state-of-the-art trackers spend a large amount of time on training the CNN-based classification networks online to adapt to the current domain. In this paper, to address the two problems, we propose a robust domain adaptation tracker based on the CNNs. The proposed tracker contains three CNNs: a local location network (LL-Net), a global location network (GL-Net), and a domain adaptation classification network (DA-Net). For the former problem, if we come to the conclusion that the tracker drifts into the background based on the output of the LL-Net, we will search for the target in a global area of the current frame based on the GL-Net. For the latter problem, we propose a CNN-based DA-Net with a domain adaptation (DA) layer. By pre-training the DA-Net offline, the DA-Net can adapt to the current domain by only updating the parameters of the DA layer in one training iteration when the online training is triggered, which makes the tracker run five times faster than MDNet with comparable tracking performance. The experimental results show that our tracker performs favorably against the state-of-the-art trackers on three popular benchmarks. |
关键词 | Convolutional Neural Networks Domain Adaptation Online Training Visual Tracking |
DOI | 10.1109/ACCESS.2018.2862878 |
收录类别 | SCI |
语种 | 英语 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23577 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Wang, Jinqiao |
作者单位 | 1.National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.R&D Center, China National Electronics Import & Export Corporation 4.Department of Medicine, Indiana University School of Medicine |
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 | Zhao, Fei,Zhang,Ting,Wu, Yi,et al. Domain Adaptation Tracker with Global and Local Searching[J]. IEEE Access,2018(6):42997 - 43008. |
APA | Zhao, Fei,Zhang,Ting,Wu, Yi,Wang, Jinqiao,&Tang, Ming.(2018).Domain Adaptation Tracker with Global and Local Searching.IEEE Access(6),42997 - 43008. |
MLA | Zhao, Fei,et al."Domain Adaptation Tracker with Global and Local Searching".IEEE Access .6(2018):42997 - 43008. |
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 | ||
ACCESS_Domain Adapta(5557KB) | 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