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. 光电技术研究所
  3. 中国科学院光电技术研究所
  4. 光电探测与信号处理研究室（五室）
Offset-Adjustable Deformable Convolution and Region Proposal Network for Visual Tracking

文献类型：期刊论文

作者Wu, Haoran1,2,3; Xu, Zhiyong1,2; Zhang, Jianlin1,2; Jia, Ge1,2
刊名IEEE Access
出版日期2019
卷号7页码:85158-85168
DOI10.1109/ACCESS.2019.2925737
文献子类期刊论文
英文摘要Spatial information is considered as the key information in many computer vision tasks including visual tracking. We attempt to use spatial information to get essential knowledge of the tracking targets in videos. Adapting to the geometry variations of the objects, the deformable convolutional networks (Deformable ConvNets) show the successful exploitation of the potential of spatial information. Through investigating the work of Deformable ConvNets, we propose the offset-adjustable deformable convolutional network for tracking. Provided with the offset adjustability technique, our network is able to have a good grasp of spatial information for the tracking objects. An appropriate target localization method is crucial to efficient tracking. One novel region proposal network with Siamese structure is designed to propose the candidate target regions and plays a vital role in promoting the effectiveness and efficiency of our model. We test our method on widely-applied OTB2015 and VOT2017 benchmark datasets. The experimental results show our method realizes state-of-the-art effects and achieves great improvement in comparison to other trackers. © 2013 IEEE.
语种英语
出版者Institute of Electrical and Electronics Engineers Inc.
源URL[http://ir.ioe.ac.cn/handle/181551/9697]  
专题光电技术研究所_光电探测与信号处理研究室（五室）
作者单位1.University of Chinese Academy of Sciences, Beijing; 100083, China;
2.Chinese Academy of Sciences, Institute of Optics and Electronics, Chengdu; 610200, China;
3.Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu; 610200, China
推荐引用方式
GB/T 7714		 Wu, Haoran,Xu, Zhiyong,Zhang, Jianlin,et al. Offset-Adjustable Deformable Convolution and Region Proposal Network for Visual Tracking[J]. IEEE Access,2019,7:85158-85168.
APA Wu, Haoran,Xu, Zhiyong,Zhang, Jianlin,&Jia, Ge.(2019).Offset-Adjustable Deformable Convolution and Region Proposal Network for Visual Tracking.IEEE Access,7,85158-85168.
MLA Wu, Haoran,et al."Offset-Adjustable Deformable Convolution and Region Proposal Network for Visual Tracking".IEEE Access 7(2019):85158-85168.

入库方式： OAI收割

来源：光电技术研究所

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。