File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/IROS45743.2020.9341784
- Scopus: eid_2-s2.0-85090241437
- WOS: WOS:000714033800041
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Towards Robust Visual Tracking for Unmanned Aerial Vehicle with Tri-Attentional Correlation Filters
Title | Towards Robust Visual Tracking for Unmanned Aerial Vehicle with Tri-Attentional Correlation Filters |
---|---|
Authors | |
Keywords | Training Visualization Correlation Unmanned aerial vehicles Spatiotemporal phenomena |
Issue Date | 2020 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000393 |
Citation | Proceedings of 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, 24 October - 24 January. 2021, p. 1575-1582 How to Cite? |
Abstract | Object tracking has been broadly applied in unmanned aerial vehicle (UAV) tasks in recent years. However, existing algorithms still face difficulties such as partial occlusion, clutter background, and other challenging visual factors. Inspired by the cutting-edge attention mechanisms, a novel object tracking framework is proposed to leverage multi-level visual attention. Three primary attention, i.e., contextual attention, dimensional attention, and spatiotemporal attention, are integrated into the training and detection stages of correlation filter-based tracking pipeline. Therefore, the proposed tracker is equipped with robust discriminative power against challenging factors while maintaining high operational efficiency in UAV scenarios. Quantitative and qualitative experiments on two well-known benchmarks with 173 challenging UAV video sequences demonstrate the effectiveness of the proposed framework. The proposed tracking algorithm favorably outperforms 12 state-of-the-art methods, yielding 4.8% relative gain in UAVDT and 8.2% relative gain in UAV123@10fps against the baseline tracker while operating at the speed of ~28 frames per second. |
Persistent Identifier | http://hdl.handle.net/10722/304070 |
ISSN | 2020 SCImago Journal Rankings: 0.597 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | He, Y | - |
dc.contributor.author | Fu, C | - |
dc.contributor.author | Lin, F | - |
dc.contributor.author | Li, Y | - |
dc.contributor.author | Lu, P | - |
dc.date.accessioned | 2021-09-23T08:54:50Z | - |
dc.date.available | 2021-09-23T08:54:50Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, 24 October - 24 January. 2021, p. 1575-1582 | - |
dc.identifier.issn | 2153-0858 | - |
dc.identifier.uri | http://hdl.handle.net/10722/304070 | - |
dc.description.abstract | Object tracking has been broadly applied in unmanned aerial vehicle (UAV) tasks in recent years. However, existing algorithms still face difficulties such as partial occlusion, clutter background, and other challenging visual factors. Inspired by the cutting-edge attention mechanisms, a novel object tracking framework is proposed to leverage multi-level visual attention. Three primary attention, i.e., contextual attention, dimensional attention, and spatiotemporal attention, are integrated into the training and detection stages of correlation filter-based tracking pipeline. Therefore, the proposed tracker is equipped with robust discriminative power against challenging factors while maintaining high operational efficiency in UAV scenarios. Quantitative and qualitative experiments on two well-known benchmarks with 173 challenging UAV video sequences demonstrate the effectiveness of the proposed framework. The proposed tracking algorithm favorably outperforms 12 state-of-the-art methods, yielding 4.8% relative gain in UAVDT and 8.2% relative gain in UAV123@10fps against the baseline tracker while operating at the speed of ~28 frames per second. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000393 | - |
dc.relation.ispartof | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Proceedings | - |
dc.rights | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Proceedings. Copyright © Institute of Electrical and Electronics Engineers. | - |
dc.rights | ©2020 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.subject | Training | - |
dc.subject | Visualization | - |
dc.subject | Correlation | - |
dc.subject | Unmanned aerial vehicles | - |
dc.subject | Spatiotemporal phenomena | - |
dc.title | Towards Robust Visual Tracking for Unmanned Aerial Vehicle with Tri-Attentional Correlation Filters | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Lu, P: lupeng@hku.hk | - |
dc.identifier.authority | Lu, P=rp02743 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/IROS45743.2020.9341784 | - |
dc.identifier.scopus | eid_2-s2.0-85090241437 | - |
dc.identifier.hkuros | 325329 | - |
dc.identifier.spage | 1575 | - |
dc.identifier.epage | 1582 | - |
dc.identifier.isi | WOS:000714033800041 | - |
dc.publisher.place | United States | - |