348 0

Long-Term Correlation Tracking

Title
Long-Term Correlation Tracking
Author
Yang, Ming-hsuan
Keywords
Target tracking; Correlation; Context; Detectors; Context modeling; Estimation
Issue Date
2015-06
Publisher
IEEE
Citation
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on 2015 June, Page. 5388-5396
Abstract
In this paper, we address the problem of long-term visual tracking where the target objects undergo significant appearance variation due to deformation, abrupt motion, heavy occlusion and out-of-view. In this setting, we decompose the task of tracking into translation and scale estimation of objects. We show that the correlation between temporal context considerably improves the accuracy and reliability for translation estimation, and it is effective to learn discriminative correlation filters from the most confident frames to estimate the scale change. In addition, we train an online random fern classifier to re-detect objects in case of tracking failure. Extensive experimental results on large-scale benchmark datasets show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy, and robustness.
URI
http://ieeexplore.ieee.org/document/7299177/?isnumber=7298593&arnumber=7299177http://hdl.handle.net/20.500.11754/25602
ISBN
978-1-4673-6964-0
ISSN
1063-6919; 1063-6919
DOI
10.1109/CVPR.2015.7299177
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE AND ENGINEERING(컴퓨터공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

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

BROWSE