An Asymmetric Feature Enhancement Network for Multiple Object Tracking of Unmanned Aerial Vehicle
Multiple object tracking (MOT) in videos captured by unmanned aerial vehicle (UAV) is a fundamental aspect of computer vision. Recently, the one-shot tracking paradigm integrates the detection and re-identification (ReID) tasks, striking a balance between tracking accuracy and inference speed. This...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/1/70 |
| _version_ | 1797358185304031232 |
|---|---|
| author | Jianbo Ma Dongxu Liu Senlin Qin Ge Jia Jianlin Zhang Zhiyong Xu |
| author_facet | Jianbo Ma Dongxu Liu Senlin Qin Ge Jia Jianlin Zhang Zhiyong Xu |
| author_sort | Jianbo Ma |
| collection | DOAJ |
| description | Multiple object tracking (MOT) in videos captured by unmanned aerial vehicle (UAV) is a fundamental aspect of computer vision. Recently, the one-shot tracking paradigm integrates the detection and re-identification (ReID) tasks, striking a balance between tracking accuracy and inference speed. This paradigm alleviates task conflicts and achieves remarkable results through various feature decoupling methods. However, in challenging scenarios like drone movements, lighting changes and object occlusion, it still encounters issues with detection failures and identity switches. In addition, traditional feature decoupling methods directly employ channel-based attention to decompose the detection and ReID branches, without a meticulous consideration of the specific requirements of each branch. To address the above problems, we introduce an asymmetric feature enhancement network with a global coordinate-aware enhancement (GCAE) module and an embedding feature aggregation (EFA) module, aiming to optimize the two branches independently. On the one hand, we develop the GCAE module for the detection branch, which effectively merges rich semantic information within the feature space to improve detection accuracy. On the other hand, we introduce the EFA module for the ReID branch, which highlights the significance of pixel-level features and acquires discriminative identity embedding through a local feature aggregation strategy. By efficiently incorporating the GCAE and EFA modules into the one-shot tracking pipeline, we present a novel MOT framework, named AsyUAV. Extensive experiments have demonstrated the effectiveness of our proposed AsyUAV. In particular, it achieves a MOTA of 38.3% and IDF1 of 51.7% on VisDrone2019, and a MOTA of 48.0% and IDF1 of 67.5% on UAVDT, outperforming existing state-of-the-art trackers. |
| first_indexed | 2024-03-08T14:58:15Z |
| format | Article |
| id | doaj.art-402694f3bd884756a55e42536b765e3c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T14:58:15Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-402694f3bd884756a55e42536b765e3c2024-01-10T15:07:18ZengMDPI AGRemote Sensing2072-42922023-12-011617010.3390/rs16010070An Asymmetric Feature Enhancement Network for Multiple Object Tracking of Unmanned Aerial VehicleJianbo Ma0Dongxu Liu1Senlin Qin2Ge Jia3Jianlin Zhang4Zhiyong Xu5National Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu 610209, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu 610209, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu 610209, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu 610209, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu 610209, ChinaNational Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu 610209, ChinaMultiple object tracking (MOT) in videos captured by unmanned aerial vehicle (UAV) is a fundamental aspect of computer vision. Recently, the one-shot tracking paradigm integrates the detection and re-identification (ReID) tasks, striking a balance between tracking accuracy and inference speed. This paradigm alleviates task conflicts and achieves remarkable results through various feature decoupling methods. However, in challenging scenarios like drone movements, lighting changes and object occlusion, it still encounters issues with detection failures and identity switches. In addition, traditional feature decoupling methods directly employ channel-based attention to decompose the detection and ReID branches, without a meticulous consideration of the specific requirements of each branch. To address the above problems, we introduce an asymmetric feature enhancement network with a global coordinate-aware enhancement (GCAE) module and an embedding feature aggregation (EFA) module, aiming to optimize the two branches independently. On the one hand, we develop the GCAE module for the detection branch, which effectively merges rich semantic information within the feature space to improve detection accuracy. On the other hand, we introduce the EFA module for the ReID branch, which highlights the significance of pixel-level features and acquires discriminative identity embedding through a local feature aggregation strategy. By efficiently incorporating the GCAE and EFA modules into the one-shot tracking pipeline, we present a novel MOT framework, named AsyUAV. Extensive experiments have demonstrated the effectiveness of our proposed AsyUAV. In particular, it achieves a MOTA of 38.3% and IDF1 of 51.7% on VisDrone2019, and a MOTA of 48.0% and IDF1 of 67.5% on UAVDT, outperforming existing state-of-the-art trackers.https://www.mdpi.com/2072-4292/16/1/70multiple object trackingdata associationfeature enhancementunmanned aerial vehicle |
| spellingShingle | Jianbo Ma Dongxu Liu Senlin Qin Ge Jia Jianlin Zhang Zhiyong Xu An Asymmetric Feature Enhancement Network for Multiple Object Tracking of Unmanned Aerial Vehicle Remote Sensing multiple object tracking data association feature enhancement unmanned aerial vehicle |
| title | An Asymmetric Feature Enhancement Network for Multiple Object Tracking of Unmanned Aerial Vehicle |
| title_full | An Asymmetric Feature Enhancement Network for Multiple Object Tracking of Unmanned Aerial Vehicle |
| title_fullStr | An Asymmetric Feature Enhancement Network for Multiple Object Tracking of Unmanned Aerial Vehicle |
| title_full_unstemmed | An Asymmetric Feature Enhancement Network for Multiple Object Tracking of Unmanned Aerial Vehicle |
| title_short | An Asymmetric Feature Enhancement Network for Multiple Object Tracking of Unmanned Aerial Vehicle |
| title_sort | asymmetric feature enhancement network for multiple object tracking of unmanned aerial vehicle |
| topic | multiple object tracking data association feature enhancement unmanned aerial vehicle |
| url | https://www.mdpi.com/2072-4292/16/1/70 |
| work_keys_str_mv | AT jianboma anasymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT dongxuliu anasymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT senlinqin anasymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT gejia anasymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT jianlinzhang anasymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT zhiyongxu anasymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT jianboma asymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT dongxuliu asymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT senlinqin asymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT gejia asymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT jianlinzhang asymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle AT zhiyongxu asymmetricfeatureenhancementnetworkformultipleobjecttrackingofunmannedaerialvehicle |