Improved YOLOv8 Network of Aircraft Target Recognition Based on Synthetic Aperture Radar Imaging Feature
The grayscale images of passenger aircraft targets obtained via Synthetic Aperture Radar (SAR) have problems such as complex airport backgrounds, significant speckle noise, and variable scales of targets. Most of the existing deep learning-based target recognition algorithms for SAR images are trans...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/10/3231 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849719418288865280 |
|---|---|
| author | Xing Wang Wen Hong Yunqing Liu Guanyu Yan Dongmei Hu Qi Jing |
| author_facet | Xing Wang Wen Hong Yunqing Liu Guanyu Yan Dongmei Hu Qi Jing |
| author_sort | Xing Wang |
| collection | DOAJ |
| description | The grayscale images of passenger aircraft targets obtained via Synthetic Aperture Radar (SAR) have problems such as complex airport backgrounds, significant speckle noise, and variable scales of targets. Most of the existing deep learning-based target recognition algorithms for SAR images are transferred from optical images, and it is difficult for them to extract the multi-dimensional features of targets comprehensively. To overcome these challenges, we proposed three enhanced methods for interpreting aircraft targets based on YOLOv8. First, we employed the Shi–Tomasi corner detection algorithm and the Enhanced Lee filtering algorithm to convert grayscale images into RGB images, thereby improving detection accuracy and efficiency. Second, we augmented the YOLOv8 model with an additional detection branch, which includes a detection head featuring the Coordinate Attention (CA) mechanism. This enhancement boosts the model’s capability to detect small and multi-scale aircraft targets. Third, we integrated the Swin Transformer mechanism into the YOLOv8 backbone, forming the C2f-SWTran module that better captures long-range dependencies in the feature map. We applied these improvements to two datasets: the ISPRS-SAR-aircraft dataset and the SAR-Aircraft-1.0 dataset. The experimental results demonstrated that our methods increased the mean Average Precision (<i>mAP</i><sub>50~95</sub>) by 2.4% and 3.4% over the YOLOv8 baseline, showing competitive advantages over other deep learning-based object detection algorithms. |
| format | Article |
| id | doaj-art-5b28658be3f14cdf8da8b4e45f0ce1be |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-5b28658be3f14cdf8da8b4e45f0ce1be2025-08-20T03:12:09ZengMDPI AGSensors1424-82202025-05-012510323110.3390/s25103231Improved YOLOv8 Network of Aircraft Target Recognition Based on Synthetic Aperture Radar Imaging FeatureXing Wang0Wen Hong1Yunqing Liu2Guanyu Yan3Dongmei Hu4Qi Jing5College of Electrical and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaCollege of Electrical and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaCollege of Electrical and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaCollege of Electrical and Information Engineering, Beihua University, Jilin 132013, ChinaCollege of Electrical and Information Engineering, Beihua University, Jilin 132013, ChinaCollege of Electrical and Information Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaThe grayscale images of passenger aircraft targets obtained via Synthetic Aperture Radar (SAR) have problems such as complex airport backgrounds, significant speckle noise, and variable scales of targets. Most of the existing deep learning-based target recognition algorithms for SAR images are transferred from optical images, and it is difficult for them to extract the multi-dimensional features of targets comprehensively. To overcome these challenges, we proposed three enhanced methods for interpreting aircraft targets based on YOLOv8. First, we employed the Shi–Tomasi corner detection algorithm and the Enhanced Lee filtering algorithm to convert grayscale images into RGB images, thereby improving detection accuracy and efficiency. Second, we augmented the YOLOv8 model with an additional detection branch, which includes a detection head featuring the Coordinate Attention (CA) mechanism. This enhancement boosts the model’s capability to detect small and multi-scale aircraft targets. Third, we integrated the Swin Transformer mechanism into the YOLOv8 backbone, forming the C2f-SWTran module that better captures long-range dependencies in the feature map. We applied these improvements to two datasets: the ISPRS-SAR-aircraft dataset and the SAR-Aircraft-1.0 dataset. The experimental results demonstrated that our methods increased the mean Average Precision (<i>mAP</i><sub>50~95</sub>) by 2.4% and 3.4% over the YOLOv8 baseline, showing competitive advantages over other deep learning-based object detection algorithms.https://www.mdpi.com/1424-8220/25/10/3231SARYOLOv8Shi–Tomasienhanced LeeCAswin transformer |
| spellingShingle | Xing Wang Wen Hong Yunqing Liu Guanyu Yan Dongmei Hu Qi Jing Improved YOLOv8 Network of Aircraft Target Recognition Based on Synthetic Aperture Radar Imaging Feature Sensors SAR YOLOv8 Shi–Tomasi enhanced Lee CA swin transformer |
| title | Improved YOLOv8 Network of Aircraft Target Recognition Based on Synthetic Aperture Radar Imaging Feature |
| title_full | Improved YOLOv8 Network of Aircraft Target Recognition Based on Synthetic Aperture Radar Imaging Feature |
| title_fullStr | Improved YOLOv8 Network of Aircraft Target Recognition Based on Synthetic Aperture Radar Imaging Feature |
| title_full_unstemmed | Improved YOLOv8 Network of Aircraft Target Recognition Based on Synthetic Aperture Radar Imaging Feature |
| title_short | Improved YOLOv8 Network of Aircraft Target Recognition Based on Synthetic Aperture Radar Imaging Feature |
| title_sort | improved yolov8 network of aircraft target recognition based on synthetic aperture radar imaging feature |
| topic | SAR YOLOv8 Shi–Tomasi enhanced Lee CA swin transformer |
| url | https://www.mdpi.com/1424-8220/25/10/3231 |
| work_keys_str_mv | AT xingwang improvedyolov8networkofaircrafttargetrecognitionbasedonsyntheticapertureradarimagingfeature AT wenhong improvedyolov8networkofaircrafttargetrecognitionbasedonsyntheticapertureradarimagingfeature AT yunqingliu improvedyolov8networkofaircrafttargetrecognitionbasedonsyntheticapertureradarimagingfeature AT guanyuyan improvedyolov8networkofaircrafttargetrecognitionbasedonsyntheticapertureradarimagingfeature AT dongmeihu improvedyolov8networkofaircrafttargetrecognitionbasedonsyntheticapertureradarimagingfeature AT qijing improvedyolov8networkofaircrafttargetrecognitionbasedonsyntheticapertureradarimagingfeature |