Improving UAV Aerial Imagery Detection Method via Superresolution Synergy
Unmanned aerial vehicles (UAVs) have emerged as versatile tools across various industries, providing valuable insights through aerial image analysis. However, the efficacy of UAV-deployed image detection systems is often limited by the resolution of captured images and the altitudinal constraints of...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10820950/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582405934809088 |
|---|---|
| author | Dianwei Wang Zehao Gao Jie Fang Yuanqing Li Zhijie Xu |
| author_facet | Dianwei Wang Zehao Gao Jie Fang Yuanqing Li Zhijie Xu |
| author_sort | Dianwei Wang |
| collection | DOAJ |
| description | Unmanned aerial vehicles (UAVs) have emerged as versatile tools across various industries, providing valuable insights through aerial image analysis. However, the efficacy of UAV-deployed image detection systems is often limited by the resolution of captured images and the altitudinal constraints of UAV operations. This article introduces a novel integration of the detection system with superresolution networks and image reconstruction techniques, inspired by the exceptional visual capabilities of eagles, to enhance image detail and detection recall from aerial perspectives. The superresolution component utilizes advanced algorithms to upscale the resolution of images captured by UAVs, thereby improving the granularity and clarity of the visual data. Concurrently, image reconstruction techniques are applied to enhance the quality of original images further. In addition, we propose an innovative adaptive feature fusion technique, which not only surpasses traditional concatenation methods in integrating multiscale features effectively but also demonstrates remarkable improvement in feature utilization and further refinement of the fusion process. Extensive experiments conducted on VisDrone2019 and DOTA datasets demonstrate that our integrated system significantly outperforms existing methods in terms of detection precision and recall. Compared to YOLOv5s, recall and mAP50 have increased by 8.89% and 11.11%, respectively, with only a slight increase in the number of parameters and complexity. |
| format | Article |
| id | doaj-art-cab8e42438744c14bf761a86d0fc148a |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-cab8e42438744c14bf761a86d0fc148a2025-01-30T00:00:14ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183959397210.1109/JSTARS.2024.352514810820950Improving UAV Aerial Imagery Detection Method via Superresolution SynergyDianwei Wang0https://orcid.org/0000-0002-6707-988XZehao Gao1https://orcid.org/0009-0005-4632-1509Jie Fang2https://orcid.org/0009-0003-9794-2917Yuanqing Li3Zhijie Xu4https://orcid.org/0000-0002-0524-5926School of Telecommunication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an, ChinaSchool of Telecommunication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an, ChinaSchool of Telecommunication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an, ChinaSchool of Telecommunication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an, ChinaSchool of Computing and Engineering, University of Huddersfield, Huddersfield, U.K.Unmanned aerial vehicles (UAVs) have emerged as versatile tools across various industries, providing valuable insights through aerial image analysis. However, the efficacy of UAV-deployed image detection systems is often limited by the resolution of captured images and the altitudinal constraints of UAV operations. This article introduces a novel integration of the detection system with superresolution networks and image reconstruction techniques, inspired by the exceptional visual capabilities of eagles, to enhance image detail and detection recall from aerial perspectives. The superresolution component utilizes advanced algorithms to upscale the resolution of images captured by UAVs, thereby improving the granularity and clarity of the visual data. Concurrently, image reconstruction techniques are applied to enhance the quality of original images further. In addition, we propose an innovative adaptive feature fusion technique, which not only surpasses traditional concatenation methods in integrating multiscale features effectively but also demonstrates remarkable improvement in feature utilization and further refinement of the fusion process. Extensive experiments conducted on VisDrone2019 and DOTA datasets demonstrate that our integrated system significantly outperforms existing methods in terms of detection precision and recall. Compared to YOLOv5s, recall and mAP50 have increased by 8.89% and 11.11%, respectively, with only a slight increase in the number of parameters and complexity.https://ieeexplore.ieee.org/document/10820950/Eagle-eye vision systemobject detectionunmanned aerial vehicle (UAV) imageryYOLOv5 |
| spellingShingle | Dianwei Wang Zehao Gao Jie Fang Yuanqing Li Zhijie Xu Improving UAV Aerial Imagery Detection Method via Superresolution Synergy IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Eagle-eye vision system object detection unmanned aerial vehicle (UAV) imagery YOLOv5 |
| title | Improving UAV Aerial Imagery Detection Method via Superresolution Synergy |
| title_full | Improving UAV Aerial Imagery Detection Method via Superresolution Synergy |
| title_fullStr | Improving UAV Aerial Imagery Detection Method via Superresolution Synergy |
| title_full_unstemmed | Improving UAV Aerial Imagery Detection Method via Superresolution Synergy |
| title_short | Improving UAV Aerial Imagery Detection Method via Superresolution Synergy |
| title_sort | improving uav aerial imagery detection method via superresolution synergy |
| topic | Eagle-eye vision system object detection unmanned aerial vehicle (UAV) imagery YOLOv5 |
| url | https://ieeexplore.ieee.org/document/10820950/ |
| work_keys_str_mv | AT dianweiwang improvinguavaerialimagerydetectionmethodviasuperresolutionsynergy AT zehaogao improvinguavaerialimagerydetectionmethodviasuperresolutionsynergy AT jiefang improvinguavaerialimagerydetectionmethodviasuperresolutionsynergy AT yuanqingli improvinguavaerialimagerydetectionmethodviasuperresolutionsynergy AT zhijiexu improvinguavaerialimagerydetectionmethodviasuperresolutionsynergy |