Ship detection using ensemble deep learning techniques from synthetic aperture radar imagery
Abstract Synthetic Aperture Radar (SAR) integrated with deep learning has been widely used in several military and civilian applications, such as border patrolling, to monitor and regulate the movement of people and goods across land, air, and maritime borders. Amongst these, maritime borders confro...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-80239-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846147930009894912 |
|---|---|
| author | Himanshu Gupta Om Prakash Verma Tarun Kumar Sharma Hirdesh Varshney Saurabh Agarwal Wooguil Pak |
| author_facet | Himanshu Gupta Om Prakash Verma Tarun Kumar Sharma Hirdesh Varshney Saurabh Agarwal Wooguil Pak |
| author_sort | Himanshu Gupta |
| collection | DOAJ |
| description | Abstract Synthetic Aperture Radar (SAR) integrated with deep learning has been widely used in several military and civilian applications, such as border patrolling, to monitor and regulate the movement of people and goods across land, air, and maritime borders. Amongst these, maritime borders confront different threats and challenges. Therefore, SAR-based ship detection becomes essential for naval surveillance in marine traffic management, oil spill detection, illegal fishing, and maritime piracy. However, the model becomes insensitive to small ships due to the wide-scale variance and uneven distribution of ship sizes in SAR images. This increases the difficulties associated with ship recognition, which triggers several false alarms. To effectively address these difficulties, the present work proposes an ensemble model (eYOLO) based on YOLOv4 and YOLOv5. The model utilizes a weighted box fusion technique to fuse the outputs of YOLOv4 and YOLOv5. Also, a generalized intersection over union loss has been adopted in eYOLO which ensures the increased generalization capability of the model with reduced scale sensitivity. The model has been developed end-to-end, and its performance has been validated against other reported results using an open-source SAR-ship dataset. The obtained results authorize the effectiveness of eYOLO in multi-scale ship detection with an F 1 score and mAP of 91.49% and 92.00%, respectively. This highlights the efficacy of eYOLO in multi-scale ship detection using SAR imagery. |
| format | Article |
| id | doaj-art-f7e3d1d5e7ec41f4b86ec8285b28d7a0 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-f7e3d1d5e7ec41f4b86ec8285b28d7a02024-12-01T12:19:24ZengNature PortfolioScientific Reports2045-23222024-11-0114111210.1038/s41598-024-80239-yShip detection using ensemble deep learning techniques from synthetic aperture radar imageryHimanshu Gupta0Om Prakash Verma1Tarun Kumar Sharma2Hirdesh Varshney3Saurabh Agarwal4Wooguil Pak5Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher EducationDepartment of Instrumentation and Control Engineering, Dr B R Ambedkar National Institute of Technology JalandharDepartment of Computer Science and Engineering, Shobhit University GangohDepartment of Computer Science and Engineering, Babu Banarasi Das UniversityDepartment of Information and Communication Engineering, Yeungnam UniversityDepartment of Information and Communication Engineering, Yeungnam UniversityAbstract Synthetic Aperture Radar (SAR) integrated with deep learning has been widely used in several military and civilian applications, such as border patrolling, to monitor and regulate the movement of people and goods across land, air, and maritime borders. Amongst these, maritime borders confront different threats and challenges. Therefore, SAR-based ship detection becomes essential for naval surveillance in marine traffic management, oil spill detection, illegal fishing, and maritime piracy. However, the model becomes insensitive to small ships due to the wide-scale variance and uneven distribution of ship sizes in SAR images. This increases the difficulties associated with ship recognition, which triggers several false alarms. To effectively address these difficulties, the present work proposes an ensemble model (eYOLO) based on YOLOv4 and YOLOv5. The model utilizes a weighted box fusion technique to fuse the outputs of YOLOv4 and YOLOv5. Also, a generalized intersection over union loss has been adopted in eYOLO which ensures the increased generalization capability of the model with reduced scale sensitivity. The model has been developed end-to-end, and its performance has been validated against other reported results using an open-source SAR-ship dataset. The obtained results authorize the effectiveness of eYOLO in multi-scale ship detection with an F 1 score and mAP of 91.49% and 92.00%, respectively. This highlights the efficacy of eYOLO in multi-scale ship detection using SAR imagery.https://doi.org/10.1038/s41598-024-80239-yEnsemble learningShip detectionSynthetic aperture radar (SAR)Weighted box fusionYOLO |
| spellingShingle | Himanshu Gupta Om Prakash Verma Tarun Kumar Sharma Hirdesh Varshney Saurabh Agarwal Wooguil Pak Ship detection using ensemble deep learning techniques from synthetic aperture radar imagery Scientific Reports Ensemble learning Ship detection Synthetic aperture radar (SAR) Weighted box fusion YOLO |
| title | Ship detection using ensemble deep learning techniques from synthetic aperture radar imagery |
| title_full | Ship detection using ensemble deep learning techniques from synthetic aperture radar imagery |
| title_fullStr | Ship detection using ensemble deep learning techniques from synthetic aperture radar imagery |
| title_full_unstemmed | Ship detection using ensemble deep learning techniques from synthetic aperture radar imagery |
| title_short | Ship detection using ensemble deep learning techniques from synthetic aperture radar imagery |
| title_sort | ship detection using ensemble deep learning techniques from synthetic aperture radar imagery |
| topic | Ensemble learning Ship detection Synthetic aperture radar (SAR) Weighted box fusion YOLO |
| url | https://doi.org/10.1038/s41598-024-80239-y |
| work_keys_str_mv | AT himanshugupta shipdetectionusingensembledeeplearningtechniquesfromsyntheticapertureradarimagery AT omprakashverma shipdetectionusingensembledeeplearningtechniquesfromsyntheticapertureradarimagery AT tarunkumarsharma shipdetectionusingensembledeeplearningtechniquesfromsyntheticapertureradarimagery AT hirdeshvarshney shipdetectionusingensembledeeplearningtechniquesfromsyntheticapertureradarimagery AT saurabhagarwal shipdetectionusingensembledeeplearningtechniquesfromsyntheticapertureradarimagery AT wooguilpak shipdetectionusingensembledeeplearningtechniquesfromsyntheticapertureradarimagery |