LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection
At present, deep learning has been widely used in SAR ship target detection, but the accurate and real-time detection of multi-scale targets still faces tough challenges. CNN-based SAR ship detectors are challenged to meet real-time requirements because of a large number of parameters. In this paper...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/19/4801 |
| _version_ | 1797477195175690240 |
|---|---|
| author | Yue Guo Shiqi Chen Ronghui Zhan Wei Wang Jun Zhang |
| author_facet | Yue Guo Shiqi Chen Ronghui Zhan Wei Wang Jun Zhang |
| author_sort | Yue Guo |
| collection | DOAJ |
| description | At present, deep learning has been widely used in SAR ship target detection, but the accurate and real-time detection of multi-scale targets still faces tough challenges. CNN-based SAR ship detectors are challenged to meet real-time requirements because of a large number of parameters. In this paper, we propose a lightweight, single-stage SAR ship target detection model called YOLO-based lightweight multi-scale ship detector (LMSD-YOLO), with better multi-scale adaptation capabilities. The proposed LMSD-YOLO consists of depthwise separable convolution, batch normalization and activate or not (ACON) activation function (DBA) module, Mobilenet with stem block (S-Mobilenet) backbone module, depthwise adaptively spatial feature fusion (DSASFF) neck module and SCYLLA-IoU (SIoU) loss function. Firstly, the DBA module is proposed as a general lightweight convolution unit to construct the whole lightweight model. Secondly, the improved S-Mobilenet module is designed as the backbone feature extraction network to enhance feature extraction ability without adding additional calculations. Then, the DSASFF module is proposed to achieve adaptive fusion of multi-scale features with fewer parameters. Finally, the SIoU is used as the loss function to accelerate model convergence and improve detection accuracy. The effectiveness of the LMSD-YOLO is validated on the SSDD, HRSID and GFSDD datasets, respectively, and the experimental results show that our proposed model has a smaller model volume and higher detection accuracy, and can accurately detect multi-scale targets in more complex scenes. The model volume of LMSD-YOLO is only 7.6MB (52.77% of model size of YOLOv5s), the detection speed on the NVIDIA AGX Xavier development board reached 68.3 FPS (32.7 FPS higher than YOLOv5s detector), indicating that the LMSD-YOLO can be easily deployed to the mobile platform for real-time application. |
| first_indexed | 2024-03-09T21:14:12Z |
| format | Article |
| id | doaj.art-a21a8d5cf8cf463b9a6d3a4c66dbe941 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:14:12Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a21a8d5cf8cf463b9a6d3a4c66dbe9412023-11-23T21:38:53ZengMDPI AGRemote Sensing2072-42922022-09-011419480110.3390/rs14194801LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship DetectionYue Guo0Shiqi Chen1Ronghui Zhan2Wei Wang3Jun Zhang4National Key Laboratory of Science and Technology on Automatic Target Recognition, College of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, College of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, College of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, College of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaNational Key Laboratory of Science and Technology on Automatic Target Recognition, College of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, ChinaAt present, deep learning has been widely used in SAR ship target detection, but the accurate and real-time detection of multi-scale targets still faces tough challenges. CNN-based SAR ship detectors are challenged to meet real-time requirements because of a large number of parameters. In this paper, we propose a lightweight, single-stage SAR ship target detection model called YOLO-based lightweight multi-scale ship detector (LMSD-YOLO), with better multi-scale adaptation capabilities. The proposed LMSD-YOLO consists of depthwise separable convolution, batch normalization and activate or not (ACON) activation function (DBA) module, Mobilenet with stem block (S-Mobilenet) backbone module, depthwise adaptively spatial feature fusion (DSASFF) neck module and SCYLLA-IoU (SIoU) loss function. Firstly, the DBA module is proposed as a general lightweight convolution unit to construct the whole lightweight model. Secondly, the improved S-Mobilenet module is designed as the backbone feature extraction network to enhance feature extraction ability without adding additional calculations. Then, the DSASFF module is proposed to achieve adaptive fusion of multi-scale features with fewer parameters. Finally, the SIoU is used as the loss function to accelerate model convergence and improve detection accuracy. The effectiveness of the LMSD-YOLO is validated on the SSDD, HRSID and GFSDD datasets, respectively, and the experimental results show that our proposed model has a smaller model volume and higher detection accuracy, and can accurately detect multi-scale targets in more complex scenes. The model volume of LMSD-YOLO is only 7.6MB (52.77% of model size of YOLOv5s), the detection speed on the NVIDIA AGX Xavier development board reached 68.3 FPS (32.7 FPS higher than YOLOv5s detector), indicating that the LMSD-YOLO can be easily deployed to the mobile platform for real-time application.https://www.mdpi.com/2072-4292/14/19/4801deep learningsynthetic aperture radar (SAR)multi-scale detectionlightweightdepthwise separable adaptively spatial feature fusion (DSASFF) |
| spellingShingle | Yue Guo Shiqi Chen Ronghui Zhan Wei Wang Jun Zhang LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection Remote Sensing deep learning synthetic aperture radar (SAR) multi-scale detection lightweight depthwise separable adaptively spatial feature fusion (DSASFF) |
| title | LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection |
| title_full | LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection |
| title_fullStr | LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection |
| title_full_unstemmed | LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection |
| title_short | LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection |
| title_sort | lmsd yolo a lightweight yolo algorithm for multi scale sar ship detection |
| topic | deep learning synthetic aperture radar (SAR) multi-scale detection lightweight depthwise separable adaptively spatial feature fusion (DSASFF) |
| url | https://www.mdpi.com/2072-4292/14/19/4801 |
| work_keys_str_mv | AT yueguo lmsdyoloalightweightyoloalgorithmformultiscalesarshipdetection AT shiqichen lmsdyoloalightweightyoloalgorithmformultiscalesarshipdetection AT ronghuizhan lmsdyoloalightweightyoloalgorithmformultiscalesarshipdetection AT weiwang lmsdyoloalightweightyoloalgorithmformultiscalesarshipdetection AT junzhang lmsdyoloalightweightyoloalgorithmformultiscalesarshipdetection |