File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICRA40945.2020.9197252
- Scopus: eid_2-s2.0-85092710476
- WOS: WOS:000712319506076
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Training-Set Distillation for Real-Time UAV Object Tracking
Title | Training-Set Distillation for Real-Time UAV Object Tracking |
---|---|
Authors | |
Keywords | Training Unmanned aerial vehicles Correlation Reliability Real-time systems |
Issue Date | 2020 |
Publisher | IEEE, Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000639 |
Citation | Proceedings of 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 31 May-31 August. 2020, p. 9715-9721 How to Cite? |
Abstract | Correlation filter (CF) has recently exhibited promising performance in visual object tracking for unmanned aerial vehicle (UAV). Such online learning method heavily depends on the quality of the training-set, yet complicated aerial scenarios like occlusion or out of view can reduce its reliability. In this work, a novel time slot-based distillation approach is proposed to efficiently and effectively optimize the training-set's quality on the fly. A cooperative energy minimization function is established to score the historical samples adaptively. To accelerate the scoring process, frames with high confident tracking results are employed as the keyframes to divide the tracking process into multiple time slots. After the establishment of a new slot, the weighted fusion of the previous samples generates one key-sample, in order to reduce the number of samples to be scored. Besides, when the current time slot exceeds the maximum frame number, which can be scored, the sample with the lowest score will be discarded. Consequently, the training-set can be efficiently and reliably distilled. Comprehensive tests on two well-known UAV benchmarks prove the effectiveness of our method with real-time speed on single CPU. |
Persistent Identifier | http://hdl.handle.net/10722/304357 |
ISSN | 2023 SCImago Journal Rankings: 1.620 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, F | - |
dc.contributor.author | Fu, C | - |
dc.contributor.author | Lin, Y | - |
dc.contributor.author | Li, Y | - |
dc.contributor.author | Lu, P | - |
dc.date.accessioned | 2021-09-23T08:58:54Z | - |
dc.date.available | 2021-09-23T08:58:54Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 31 May-31 August. 2020, p. 9715-9721 | - |
dc.identifier.issn | 1050-4729 | - |
dc.identifier.uri | http://hdl.handle.net/10722/304357 | - |
dc.description.abstract | Correlation filter (CF) has recently exhibited promising performance in visual object tracking for unmanned aerial vehicle (UAV). Such online learning method heavily depends on the quality of the training-set, yet complicated aerial scenarios like occlusion or out of view can reduce its reliability. In this work, a novel time slot-based distillation approach is proposed to efficiently and effectively optimize the training-set's quality on the fly. A cooperative energy minimization function is established to score the historical samples adaptively. To accelerate the scoring process, frames with high confident tracking results are employed as the keyframes to divide the tracking process into multiple time slots. After the establishment of a new slot, the weighted fusion of the previous samples generates one key-sample, in order to reduce the number of samples to be scored. Besides, when the current time slot exceeds the maximum frame number, which can be scored, the sample with the lowest score will be discarded. Consequently, the training-set can be efficiently and reliably distilled. Comprehensive tests on two well-known UAV benchmarks prove the effectiveness of our method with real-time speed on single CPU. | - |
dc.language | eng | - |
dc.publisher | IEEE, Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000639 | - |
dc.relation.ispartof | IEEE International Conference on Robotics and Automation (ICRA) | - |
dc.rights | IEEE International Conference on Robotics and Automation (ICRA). Copyright © IEEE, Computer Society. | - |
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 | Unmanned aerial vehicles | - |
dc.subject | Correlation | - |
dc.subject | Reliability | - |
dc.subject | Real-time systems | - |
dc.title | Training-Set Distillation for Real-Time UAV Object Tracking | - |
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/ICRA40945.2020.9197252 | - |
dc.identifier.scopus | eid_2-s2.0-85092710476 | - |
dc.identifier.hkuros | 325326 | - |
dc.identifier.spage | 9715 | - |
dc.identifier.epage | 9721 | - |
dc.identifier.isi | WOS:000712319506076 | - |
dc.publisher.place | United States | - |