File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Intermittent contextual learning for keyfilter-aware uav object tracking using deep convolutional feature

TitleIntermittent contextual learning for keyfilter-aware uav object tracking using deep convolutional feature
Authors
KeywordsUnmanned aerial vehicles
Correlation
Visualization
Training
Object tracking
Issue Date2020
PublisherIEEE. The Journal's web site is located at http://www.ieee.org/organizations/tab/tmm.html
Citation
IEEE Transactions on Multimedia, 2020, Epub 2020-04-23 How to Cite?
AbstractVisual tracking, one of the most favorable multimedia applications, has been widely used in unmanned aerial vehicle (UAV) for civil infrastructure monitoring, aerial cinematography, autonomous navigation, etc. Most existing trackers utilize deep convolutional feature to enhance tracking robustness in scenarios of various appearance variation. However, they commonly neglect speed which is crucial for UAV with restricted calculation resources. In this work, a novel correlation filter-based keyfilteraware tracker with a new intermittent context learning strategy is proposed to efficiently and effectively alleviate the problems of background clutter, deficient description, occlusion, illumination change, etc. Specifically, context information is utilized to empower the filter higher discriminating ability through response repression of the omnidirectional context patches. Furthermore, keyfilter is produced from the periodically selected keyframe. The latest produced keyfilter is used to restrain the current filter's corrupted changes. Most importantly, context learning of correlation filter is implemented intermittently to fully increase the tracking efficiency. This intermittent learning strategy can ensure every filter maintain context awareness owing to the restriction of keyfilter, periodically enhancing the context awareness. Additionally, hand crafted and deep features are fused to establish a comprehensive appearance model of the tracked object. Substantial experiments on three challenging UAV benchmarks totally with 213 image sequences have shown that our tracker surpasses the state-of-the-art results, and exhibits a remarkable generality in short-term and long-term UAV tracking tasks as well as a variety of challenging attributes.
Persistent Identifierhttp://hdl.handle.net/10722/284899
ISSN
2019 Impact Factor: 6.051
2015 SCImago Journal Rankings: 1.603

 

DC FieldValueLanguage
dc.contributor.authorLi, Y-
dc.contributor.authorFu, C-
dc.contributor.authorHuang, Z-
dc.contributor.authorZhang, Y-
dc.contributor.authorPan, J-
dc.date.accessioned2020-08-07T09:04:05Z-
dc.date.available2020-08-07T09:04:05Z-
dc.date.issued2020-
dc.identifier.citationIEEE Transactions on Multimedia, 2020, Epub 2020-04-23-
dc.identifier.issn1520-9210-
dc.identifier.urihttp://hdl.handle.net/10722/284899-
dc.description.abstractVisual tracking, one of the most favorable multimedia applications, has been widely used in unmanned aerial vehicle (UAV) for civil infrastructure monitoring, aerial cinematography, autonomous navigation, etc. Most existing trackers utilize deep convolutional feature to enhance tracking robustness in scenarios of various appearance variation. However, they commonly neglect speed which is crucial for UAV with restricted calculation resources. In this work, a novel correlation filter-based keyfilteraware tracker with a new intermittent context learning strategy is proposed to efficiently and effectively alleviate the problems of background clutter, deficient description, occlusion, illumination change, etc. Specifically, context information is utilized to empower the filter higher discriminating ability through response repression of the omnidirectional context patches. Furthermore, keyfilter is produced from the periodically selected keyframe. The latest produced keyfilter is used to restrain the current filter's corrupted changes. Most importantly, context learning of correlation filter is implemented intermittently to fully increase the tracking efficiency. This intermittent learning strategy can ensure every filter maintain context awareness owing to the restriction of keyfilter, periodically enhancing the context awareness. Additionally, hand crafted and deep features are fused to establish a comprehensive appearance model of the tracked object. Substantial experiments on three challenging UAV benchmarks totally with 213 image sequences have shown that our tracker surpasses the state-of-the-art results, and exhibits a remarkable generality in short-term and long-term UAV tracking tasks as well as a variety of challenging attributes.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at http://www.ieee.org/organizations/tab/tmm.html-
dc.relation.ispartofIEEE Transactions on Multimedia-
dc.rightsIEEE Transactions on Multimedia. Copyright © IEEE.-
dc.rights©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectUnmanned aerial vehicles-
dc.subjectCorrelation-
dc.subjectVisualization-
dc.subjectTraining-
dc.subjectObject tracking-
dc.titleIntermittent contextual learning for keyfilter-aware uav object tracking using deep convolutional feature-
dc.typeArticle-
dc.identifier.emailPan, J: jpan@cs.hku.hk-
dc.identifier.authorityPan, J=rp01984-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TMM.2020.2990064-
dc.identifier.hkuros312100-
dc.identifier.volumeEpub 2020-04-23-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats