LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport Surface
The introduction of various deep neural network architectures has greatly advanced aircraft pose estimation using high-resolution images. However, realistic airport surface monitors typically take low-resolution (LR) images, and the results of the aircraft pose estimation are far from being accurate...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/3/1248 |
| _version_ | 1797623299186884608 |
|---|---|
| author | Xinyang Yuan Daoyong Fu Songchen Han |
| author_facet | Xinyang Yuan Daoyong Fu Songchen Han |
| author_sort | Xinyang Yuan |
| collection | DOAJ |
| description | The introduction of various deep neural network architectures has greatly advanced aircraft pose estimation using high-resolution images. However, realistic airport surface monitors typically take low-resolution (LR) images, and the results of the aircraft pose estimation are far from being accurate enough to be considered acceptable because of long-range capture. To fill this gap, we propose a brand-new, end-to-end low-resolution aircraft pose estimate network (LRF-SRNet) to address the problem of estimating the pose of poor-quality airport surface surveillance aircraft images. The method successfully combines the pose estimation method with the super-resolution (SR) technique. Specifically, to reconstruct high-resolution aircraft images, a super-resolution network (SRNet) is created. In addition, an essential component termed the large receptive field block (LRF block) helps estimate the aircraft’s pose. By broadening the neural network’s receptive field, it enables the perception of the aircraft’s structure. Experimental results demonstrate that, on the airport surface surveillance dataset, our method performs significantly better than the most widely used baseline methods, with AP exceeding Baseline and HRNet by 3.1% and 4.5%. |
| first_indexed | 2024-03-11T09:26:42Z |
| format | Article |
| id | doaj.art-f45097451f7a424394b6ec57f74a7beb |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T09:26:42Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f45097451f7a424394b6ec57f74a7beb2023-11-16T17:58:17ZengMDPI AGSensors1424-82202023-01-01233124810.3390/s23031248LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport SurfaceXinyang Yuan0Daoyong Fu1Songchen Han2School of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, ChinaSchool of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, ChinaThe introduction of various deep neural network architectures has greatly advanced aircraft pose estimation using high-resolution images. However, realistic airport surface monitors typically take low-resolution (LR) images, and the results of the aircraft pose estimation are far from being accurate enough to be considered acceptable because of long-range capture. To fill this gap, we propose a brand-new, end-to-end low-resolution aircraft pose estimate network (LRF-SRNet) to address the problem of estimating the pose of poor-quality airport surface surveillance aircraft images. The method successfully combines the pose estimation method with the super-resolution (SR) technique. Specifically, to reconstruct high-resolution aircraft images, a super-resolution network (SRNet) is created. In addition, an essential component termed the large receptive field block (LRF block) helps estimate the aircraft’s pose. By broadening the neural network’s receptive field, it enables the perception of the aircraft’s structure. Experimental results demonstrate that, on the airport surface surveillance dataset, our method performs significantly better than the most widely used baseline methods, with AP exceeding Baseline and HRNet by 3.1% and 4.5%.https://www.mdpi.com/1424-8220/23/3/1248aircraft pose estimationsuper resolutionreceptive field |
| spellingShingle | Xinyang Yuan Daoyong Fu Songchen Han LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport Surface Sensors aircraft pose estimation super resolution receptive field |
| title | LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport Surface |
| title_full | LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport Surface |
| title_fullStr | LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport Surface |
| title_full_unstemmed | LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport Surface |
| title_short | LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport Surface |
| title_sort | lrf srnet large scale super resolution network for estimating aircraft pose on the airport surface |
| topic | aircraft pose estimation super resolution receptive field |
| url | https://www.mdpi.com/1424-8220/23/3/1248 |
| work_keys_str_mv | AT xinyangyuan lrfsrnetlargescalesuperresolutionnetworkforestimatingaircraftposeontheairportsurface AT daoyongfu lrfsrnetlargescalesuperresolutionnetworkforestimatingaircraftposeontheairportsurface AT songchenhan lrfsrnetlargescalesuperresolutionnetworkforestimatingaircraftposeontheairportsurface |