CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 视频内容安全
Visual Tracking via Spatially Aligned Correlation Filters Network
Zhang, Mengdan1; Wang, Qiang1; Xing, Junliang1; Gao, Jin1; Peng, Peixi1; Hu, Weiming1; Maybank, Steve2
2018
Conference Name15th European Conference on Computer Vision, ECCV 2018
Conference DateSeptember 8, 2018 - September 14, 2018
Conference PlaceMunich, Germany
Abstract

Correlation filters based trackers rely on a periodic assumption of the search sample to efficiently distinguish the target from the background. This assumption however yields undesired boundary effects and restricts aspect ratios of search samples. To handle these issues, an end-to-end deep architecture is proposed to incorporate geometric transformations into a correlation filters based network. This architecture introduces a novel spatial alignmentmodule, which provides continuous feedback for transforming the target from the border to the center with a normalized aspect ratio. It enables correlation filters to work on well-aligned samples for better tracking. The whole architecture not only learns a generic relationship between object geometric transformations and object appearances, but also learns robust representations coupled to correlation filters in case of various geometric transformations. This lightweight architecture permits real-time speed. Experiments show our tracker effectively handles boundary effects and aspect ratio variations, achieving state-of-the-art tracking results on recent benchmarks.

Indexed ByEI
Language英语
Sub direction classification目标检测、跟踪与识别
planning direction of the national heavy laboratory实体人工智能系统感认知
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57504
Collection多模态人工智能系统全国重点实验室_视频内容安全
Affiliation1.CAS Center for Excellence in Brain Science and Intelligence Technology, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China
2.Birkbeck College, University of London, London, United Kingdom
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Mengdan,Wang, Qiang,Xing, Junliang,et al. Visual Tracking via Spatially Aligned Correlation Filters Network[C],2018.
Files in This Item:
File Name/Size DocType Version Access License
mengdan_zhang_Visual(1118KB)会议论文 开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Mengdan]'s Articles
[Wang, Qiang]'s Articles
[Xing, Junliang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Mengdan]'s Articles
[Wang, Qiang]'s Articles
[Xing, Junliang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Mengdan]'s Articles
[Wang, Qiang]'s Articles
[Xing, Junliang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: mengdan_zhang_Visual_Tracking_via_ECCV_2018_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.