TPH-YOLOv5-Air: Airport Confusing Object Detection via Adaptively Spatial Feature Fusion
Airport detection in remote sensing scenes is a crucial area of research, playing a key role in aircraft blind landing procedures. However, airport detection in remote sensing scenes still faces challenges such as class confusion, poor detection performance on multi-scale objects, and limited datase...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/15/3883 |
| _version_ | 1797586014956421120 |
|---|---|
| author | Qiang Wang Wenquan Feng Lifan Yao Chen Zhuang Binghao Liu Lijiang Chen |
| author_facet | Qiang Wang Wenquan Feng Lifan Yao Chen Zhuang Binghao Liu Lijiang Chen |
| author_sort | Qiang Wang |
| collection | DOAJ |
| description | Airport detection in remote sensing scenes is a crucial area of research, playing a key role in aircraft blind landing procedures. However, airport detection in remote sensing scenes still faces challenges such as class confusion, poor detection performance on multi-scale objects, and limited dataset availability. To address these issues, this paper proposes a novel airport detection network (TPH-YOLOv5-Air) based on adaptive spatial feature fusion (ASFF). Firstly, we construct an Airport Confusing Object Dataset (ACD) specifically tailored for remote sensing scenarios containing 9501 instances of airport confusion objects. Secondly, building upon the foundation of TPH-YOLOv5++, we adopt the ASFF structure, which not only enhances the feature extraction efficiency but also enriches feature representation. Moreover, an adaptive spatial feature fusion (ASFF) strategy based on adaptive parameter adjustment module (APAM) is proposed, which improves the feature scale invariance and enhances the detection of airports. Finally, experimental results based on the ACD dataset demonstrate that TPH-YOLOv5-Air achieves a mean average precision (mAP) of 49.4%, outperforming TPH-YOLOv5++ by 2% and the original YOLOv5 network by 3.6%. This study contributes to the advancement of airport detection in remote sensing scenes and demonstrates the practical application potential of TPH-YOLOv5-Air in this domain. Visualization and analysis further validate the effectiveness and interpretability of TPH-YOLOv5-Air. The ACD dataset is publicly available. |
| first_indexed | 2024-03-11T00:17:18Z |
| format | Article |
| id | doaj.art-3fdfc9891c974770bf7d867233691f7d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T00:17:18Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3fdfc9891c974770bf7d867233691f7d2023-11-18T23:32:09ZengMDPI AGRemote Sensing2072-42922023-08-011515388310.3390/rs15153883TPH-YOLOv5-Air: Airport Confusing Object Detection via Adaptively Spatial Feature FusionQiang Wang0Wenquan Feng1Lifan Yao2Chen Zhuang3Binghao Liu4Lijiang Chen5Department of Electrics and Information Engineering, Beihang University, Beijing 100191, ChinaDepartment of Electrics and Information Engineering, Beihang University, Beijing 100191, ChinaQingdao Research Institute of Beihang University, Qingdao 266000, ChinaDepartment of Electrics and Information Engineering, Beihang University, Beijing 100191, ChinaDepartment of Electrics and Information Engineering, Beihang University, Beijing 100191, ChinaDepartment of Electrics and Information Engineering, Beihang University, Beijing 100191, ChinaAirport detection in remote sensing scenes is a crucial area of research, playing a key role in aircraft blind landing procedures. However, airport detection in remote sensing scenes still faces challenges such as class confusion, poor detection performance on multi-scale objects, and limited dataset availability. To address these issues, this paper proposes a novel airport detection network (TPH-YOLOv5-Air) based on adaptive spatial feature fusion (ASFF). Firstly, we construct an Airport Confusing Object Dataset (ACD) specifically tailored for remote sensing scenarios containing 9501 instances of airport confusion objects. Secondly, building upon the foundation of TPH-YOLOv5++, we adopt the ASFF structure, which not only enhances the feature extraction efficiency but also enriches feature representation. Moreover, an adaptive spatial feature fusion (ASFF) strategy based on adaptive parameter adjustment module (APAM) is proposed, which improves the feature scale invariance and enhances the detection of airports. Finally, experimental results based on the ACD dataset demonstrate that TPH-YOLOv5-Air achieves a mean average precision (mAP) of 49.4%, outperforming TPH-YOLOv5++ by 2% and the original YOLOv5 network by 3.6%. This study contributes to the advancement of airport detection in remote sensing scenes and demonstrates the practical application potential of TPH-YOLOv5-Air in this domain. Visualization and analysis further validate the effectiveness and interpretability of TPH-YOLOv5-Air. The ACD dataset is publicly available.https://www.mdpi.com/2072-4292/15/15/3883airport detectionremote sensing scene imageryAirport Confusing Object Dataset (ACD)TPH-YOLOv5-AirAPAM |
| spellingShingle | Qiang Wang Wenquan Feng Lifan Yao Chen Zhuang Binghao Liu Lijiang Chen TPH-YOLOv5-Air: Airport Confusing Object Detection via Adaptively Spatial Feature Fusion Remote Sensing airport detection remote sensing scene imagery Airport Confusing Object Dataset (ACD) TPH-YOLOv5-Air APAM |
| title | TPH-YOLOv5-Air: Airport Confusing Object Detection via Adaptively Spatial Feature Fusion |
| title_full | TPH-YOLOv5-Air: Airport Confusing Object Detection via Adaptively Spatial Feature Fusion |
| title_fullStr | TPH-YOLOv5-Air: Airport Confusing Object Detection via Adaptively Spatial Feature Fusion |
| title_full_unstemmed | TPH-YOLOv5-Air: Airport Confusing Object Detection via Adaptively Spatial Feature Fusion |
| title_short | TPH-YOLOv5-Air: Airport Confusing Object Detection via Adaptively Spatial Feature Fusion |
| title_sort | tph yolov5 air airport confusing object detection via adaptively spatial feature fusion |
| topic | airport detection remote sensing scene imagery Airport Confusing Object Dataset (ACD) TPH-YOLOv5-Air APAM |
| url | https://www.mdpi.com/2072-4292/15/15/3883 |
| work_keys_str_mv | AT qiangwang tphyolov5airairportconfusingobjectdetectionviaadaptivelyspatialfeaturefusion AT wenquanfeng tphyolov5airairportconfusingobjectdetectionviaadaptivelyspatialfeaturefusion AT lifanyao tphyolov5airairportconfusingobjectdetectionviaadaptivelyspatialfeaturefusion AT chenzhuang tphyolov5airairportconfusingobjectdetectionviaadaptivelyspatialfeaturefusion AT binghaoliu tphyolov5airairportconfusingobjectdetectionviaadaptivelyspatialfeaturefusion AT lijiangchen tphyolov5airairportconfusingobjectdetectionviaadaptivelyspatialfeaturefusion |