Unified Detection and Feature Extraction of Ships in Satellite Images
The increasing importance of maritime surveillance, particularly in monitoring dark ships, highlights the need for advanced detection models that go beyond simple ship localisation. Current approaches largely focus on either detection or feature extraction, leaving a gap in unified methods capable o...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/24/4719 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846102861469974528 |
|---|---|
| author | Kristian Aalling Sørensen Peder Heiselberg Henning Heiselberg |
| author_facet | Kristian Aalling Sørensen Peder Heiselberg Henning Heiselberg |
| author_sort | Kristian Aalling Sørensen |
| collection | DOAJ |
| description | The increasing importance of maritime surveillance, particularly in monitoring dark ships, highlights the need for advanced detection models that go beyond simple ship localisation. Current approaches largely focus on either detection or feature extraction, leaving a gap in unified methods capable of providing detailed ship characteristics. This study addresses this gap by developing a unified model for ship detection and characterisation from Synthetic Aperture Radar images, estimating features such as true length, true breadth, and heading. The model is designed to detect ships of varying sizes while simultaneously estimating their characteristics, and experimental results show a high detection accuracy, with a recall of 87.7% and an F1-score of 93.5%. The model also effectively estimates ship dimensions, with mean errors of 1.4 ± 16.2 m for length and 1.5 ± 4.5 m for breadth. Estimating the heading proved challenging for smaller ships, but was accurate for larger ships. A total of 50% of the heading estimates were within 15 degrees of error. This unified approach offers practical benefits for maritime operations. It is especially useful in situations where both ship detection and detailed information are needed, such as predicting future ship positions or identifying ships. |
| format | Article |
| id | doaj-art-8270aa1ca3a14c26b76cbf9217255ab0 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-8270aa1ca3a14c26b76cbf9217255ab02024-12-27T14:51:00ZengMDPI AGRemote Sensing2072-42922024-12-011624471910.3390/rs16244719Unified Detection and Feature Extraction of Ships in Satellite ImagesKristian Aalling Sørensen0Peder Heiselberg1Henning Heiselberg2DTU Security, National Space Institute, Technical University of Denmark, 2800 Kongens Lyngby, DenmarkGeodesy and Earth Observation, National Space Institute, Technical University of Denmark, 2800 Kongens Lyngby, DenmarkDTU Security, National Space Institute, Technical University of Denmark, 2800 Kongens Lyngby, DenmarkThe increasing importance of maritime surveillance, particularly in monitoring dark ships, highlights the need for advanced detection models that go beyond simple ship localisation. Current approaches largely focus on either detection or feature extraction, leaving a gap in unified methods capable of providing detailed ship characteristics. This study addresses this gap by developing a unified model for ship detection and characterisation from Synthetic Aperture Radar images, estimating features such as true length, true breadth, and heading. The model is designed to detect ships of varying sizes while simultaneously estimating their characteristics, and experimental results show a high detection accuracy, with a recall of 87.7% and an F1-score of 93.5%. The model also effectively estimates ship dimensions, with mean errors of 1.4 ± 16.2 m for length and 1.5 ± 4.5 m for breadth. Estimating the heading proved challenging for smaller ships, but was accurate for larger ships. A total of 50% of the heading estimates were within 15 degrees of error. This unified approach offers practical benefits for maritime operations. It is especially useful in situations where both ship detection and detailed information are needed, such as predicting future ship positions or identifying ships.https://www.mdpi.com/2072-4292/16/24/4719Synthetic Aperture Radar (SAR)maritime domain awarenessship detectionship feature extractiondeep learning |
| spellingShingle | Kristian Aalling Sørensen Peder Heiselberg Henning Heiselberg Unified Detection and Feature Extraction of Ships in Satellite Images Remote Sensing Synthetic Aperture Radar (SAR) maritime domain awareness ship detection ship feature extraction deep learning |
| title | Unified Detection and Feature Extraction of Ships in Satellite Images |
| title_full | Unified Detection and Feature Extraction of Ships in Satellite Images |
| title_fullStr | Unified Detection and Feature Extraction of Ships in Satellite Images |
| title_full_unstemmed | Unified Detection and Feature Extraction of Ships in Satellite Images |
| title_short | Unified Detection and Feature Extraction of Ships in Satellite Images |
| title_sort | unified detection and feature extraction of ships in satellite images |
| topic | Synthetic Aperture Radar (SAR) maritime domain awareness ship detection ship feature extraction deep learning |
| url | https://www.mdpi.com/2072-4292/16/24/4719 |
| work_keys_str_mv | AT kristianaallingsørensen unifieddetectionandfeatureextractionofshipsinsatelliteimages AT pederheiselberg unifieddetectionandfeatureextractionofshipsinsatelliteimages AT henningheiselberg unifieddetectionandfeatureextractionofshipsinsatelliteimages |