File Download

There are no files associated with this item.

Supplementary

Conference Paper: Augmented Memory For Correlation Filters In Real-time Uav Tracking

TitleAugmented Memory For Correlation Filters In Real-time Uav Tracking
Authors
KeywordsAerial Systems
Perception and Autonomy
Computer Vision for Automation
Computer Vision for Other Robotic Applications
Issue Date2020
Citation
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): Consumer Robots and Our Future, Virtual Conference, Las Vegas, USA, 25-29 October 2020 How to Cite?
AbstractThe outstanding computational efficiency of discriminative correlation filter (DCF) fades away with various complicated improvements. Previous appearances are also gradually forgotten due to the exponential decay of historical views in traditional appearance updating scheme of DCF framework, reducing the model’s robustness. In this work, a novel tracker based on DCF framework is proposed to augment memory of previously appeared views while running at real-time speed. Several historical views and the current view are simultaneously introduced in training to allow the tracker to adapt to new appearances as well as memorize previous ones. A novel rapid compressed context learning is proposed to increase the discriminative ability of the filter efficiently. Substantial experiments on UAVDT and UAV123 datasets have validated that the proposed tracker performs competitively against other 26 top DCF and deep-based trackers with over 40fps on CPU.
DescriptionMoAT20 Aerial Systems: Perception - Paper MoAT20.3
Persistent Identifierhttp://hdl.handle.net/10722/284881

 

DC FieldValueLanguage
dc.contributor.authorLI, Y-
dc.contributor.authorFU, C-
dc.contributor.authorDING, F-
dc.contributor.authorHUANG, Z-
dc.contributor.authorPan, J-
dc.date.accessioned2020-08-07T09:03:51Z-
dc.date.available2020-08-07T09:03:51Z-
dc.date.issued2020-
dc.identifier.citationIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): Consumer Robots and Our Future, Virtual Conference, Las Vegas, USA, 25-29 October 2020-
dc.identifier.urihttp://hdl.handle.net/10722/284881-
dc.descriptionMoAT20 Aerial Systems: Perception - Paper MoAT20.3-
dc.description.abstractThe outstanding computational efficiency of discriminative correlation filter (DCF) fades away with various complicated improvements. Previous appearances are also gradually forgotten due to the exponential decay of historical views in traditional appearance updating scheme of DCF framework, reducing the model’s robustness. In this work, a novel tracker based on DCF framework is proposed to augment memory of previously appeared views while running at real-time speed. Several historical views and the current view are simultaneously introduced in training to allow the tracker to adapt to new appearances as well as memorize previous ones. A novel rapid compressed context learning is proposed to increase the discriminative ability of the filter efficiently. Substantial experiments on UAVDT and UAV123 datasets have validated that the proposed tracker performs competitively against other 26 top DCF and deep-based trackers with over 40fps on CPU.-
dc.languageeng-
dc.relation.ispartofIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)-
dc.subjectAerial Systems-
dc.subjectPerception and Autonomy-
dc.subjectComputer Vision for Automation-
dc.subjectComputer Vision for Other Robotic Applications-
dc.titleAugmented Memory For Correlation Filters In Real-time Uav Tracking-
dc.typeConference_Paper-
dc.identifier.emailPan, J: jpan@cs.hku.hk-
dc.identifier.authorityPan, J=rp01984-
dc.identifier.hkuros312165-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats