A multi-scale enhanced feature fusion model for aircraft detection from SAR images

Aircraft detection has been a challenging task although many efforts have been made due to the diversity of aircraft scale and interference of complicated background in synthetic aperture radar (SAR) images. So, this paper proposes a new method, named ‘multi-scale enhanced feature fusion network, br...

Full description

Saved in:
Bibliographic Details
Main Authors: Guoqing Zhou, Ziqi Zhang, Feng Wang, Qiang Zhu, YueFeng Wang, Ertao Gao, Yufu Cai, Xiao Zhou, Cong Li
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2507842
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224336566648832
author Guoqing Zhou
Ziqi Zhang
Feng Wang
Qiang Zhu
YueFeng Wang
Ertao Gao
Yufu Cai
Xiao Zhou
Cong Li
author_facet Guoqing Zhou
Ziqi Zhang
Feng Wang
Qiang Zhu
YueFeng Wang
Ertao Gao
Yufu Cai
Xiao Zhou
Cong Li
author_sort Guoqing Zhou
collection DOAJ
description Aircraft detection has been a challenging task although many efforts have been made due to the diversity of aircraft scale and interference of complicated background in synthetic aperture radar (SAR) images. So, this paper proposes a new method, named ‘multi-scale enhanced feature fusion network, briefly, MSEFF-Net’. Firstly, a nonlinear activation free attention module (NAFAM) is proposed to enhance the feature information of aircraft. Secondly, a feature fusion module (FFM) is designed and a multi-scale feature fusion pyramid network (MFFPN) is proposed to integrate the semantic information of different layers. Finally, a global-to-local context aggregation (GLCA) module is built to aggregate global and local information. The proposed model is validated using two groups of public datasets, SAR-AIRcraft-1.0 and SADD, and is compared with various advanced detection methods (e.g. Faster R-CNN, Cascade-RCNN, YOLO series and RT-DETR series). The experimental results demonstrate that the precision, the recall, and the mAP50 reach 97.4%, 97.6%, 98.9% for SADD dataset; the mAP50 and the mAP50:95 reach 70.1% and 49.0% for SAR-AIRcraft-1.0 dataset, respectively. The results indicate that the proposed method achieves higher accuracy than the other detection methods do.
format Article
id doaj-art-fe2443b7a51e4cb595e9a6fa96901d3f
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-fe2443b7a51e4cb595e9a6fa96901d3f2025-08-25T11:32:04ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2507842A multi-scale enhanced feature fusion model for aircraft detection from SAR imagesGuoqing Zhou0Ziqi Zhang1Feng Wang2Qiang Zhu3YueFeng Wang4Ertao Gao5Yufu Cai6Xiao Zhou7Cong Li8Guangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaGuangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaGuangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaGuangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaGuangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaGuangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaGuangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaGuangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaGuangxi Key Laboratory of Spatial Information and Geomatics, College of Geomatics and Geoinformation, Guilin University of Technology, Guilin, People’s Republic of ChinaAircraft detection has been a challenging task although many efforts have been made due to the diversity of aircraft scale and interference of complicated background in synthetic aperture radar (SAR) images. So, this paper proposes a new method, named ‘multi-scale enhanced feature fusion network, briefly, MSEFF-Net’. Firstly, a nonlinear activation free attention module (NAFAM) is proposed to enhance the feature information of aircraft. Secondly, a feature fusion module (FFM) is designed and a multi-scale feature fusion pyramid network (MFFPN) is proposed to integrate the semantic information of different layers. Finally, a global-to-local context aggregation (GLCA) module is built to aggregate global and local information. The proposed model is validated using two groups of public datasets, SAR-AIRcraft-1.0 and SADD, and is compared with various advanced detection methods (e.g. Faster R-CNN, Cascade-RCNN, YOLO series and RT-DETR series). The experimental results demonstrate that the precision, the recall, and the mAP50 reach 97.4%, 97.6%, 98.9% for SADD dataset; the mAP50 and the mAP50:95 reach 70.1% and 49.0% for SAR-AIRcraft-1.0 dataset, respectively. The results indicate that the proposed method achieves higher accuracy than the other detection methods do.https://www.tandfonline.com/doi/10.1080/17538947.2025.2507842Synthetic aperture radar (SAR)aircraft detectionattention mechanismmulti-scale feature fusionYOLOv8
spellingShingle Guoqing Zhou
Ziqi Zhang
Feng Wang
Qiang Zhu
YueFeng Wang
Ertao Gao
Yufu Cai
Xiao Zhou
Cong Li
A multi-scale enhanced feature fusion model for aircraft detection from SAR images
International Journal of Digital Earth
Synthetic aperture radar (SAR)
aircraft detection
attention mechanism
multi-scale feature fusion
YOLOv8
title A multi-scale enhanced feature fusion model for aircraft detection from SAR images
title_full A multi-scale enhanced feature fusion model for aircraft detection from SAR images
title_fullStr A multi-scale enhanced feature fusion model for aircraft detection from SAR images
title_full_unstemmed A multi-scale enhanced feature fusion model for aircraft detection from SAR images
title_short A multi-scale enhanced feature fusion model for aircraft detection from SAR images
title_sort multi scale enhanced feature fusion model for aircraft detection from sar images
topic Synthetic aperture radar (SAR)
aircraft detection
attention mechanism
multi-scale feature fusion
YOLOv8
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2507842
work_keys_str_mv AT guoqingzhou amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT ziqizhang amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT fengwang amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT qiangzhu amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT yuefengwang amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT ertaogao amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT yufucai amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT xiaozhou amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT congli amultiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT guoqingzhou multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT ziqizhang multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT fengwang multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT qiangzhu multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT yuefengwang multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT ertaogao multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT yufucai multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT xiaozhou multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages
AT congli multiscaleenhancedfeaturefusionmodelforaircraftdetectionfromsarimages