iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applications
This article describes a comprehensive Synthetic Aperture Radar (SAR) satellite based ships dataset for use in state of the art object detection algorithms. The dataset comprises 11,590 image tiles containing 27,885 ships examples. Each image tile has spatial dimensions of 512 × 512 pixels and is ex...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Data in Brief |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352340923006054 |
| _version_ | 1797660460815745024 |
|---|---|
| author | Muhammad Farhan Humayun Farrukh Aziz Bhatti Khurram Khurshid |
| author_facet | Muhammad Farhan Humayun Farrukh Aziz Bhatti Khurram Khurshid |
| author_sort | Muhammad Farhan Humayun |
| collection | DOAJ |
| description | This article describes a comprehensive Synthetic Aperture Radar (SAR) satellite based ships dataset for use in state of the art object detection algorithms. The dataset comprises 11,590 image tiles containing 27,885 ships examples. Each image tile has spatial dimensions of 512 × 512 pixels and is exported in JPEG format. The dataset contains a wide variety of inshore and offshore scenes under varying background settings and sea conditions to generate an all-inclusive understanding of the ship detection task in SAR satellite images. The dataset is generated using images from six different satellite sensors covering a wide range of electromagnetic spectrum including C, L and X band radar imaging frequencies. All the sensors have different resolutions and imaging modes. The dataset is randomly distributed into training, validation and test sets in the ratio of 70:20:10, respectively, for ease of comparison and bench-marking. The dataset was conceptualized, processed, labeled and verified at the Artificial Intelligence and Computer Vision (iVision) Lab at the Institute of Space Technology, Pakistan. To the best of our knowledge, this is the most diverse satellite based SAR ships dataset available in the public domain in terms of satellite sensors, radar imaging frequencies and background settings. The dataset can be used to train and optimize deep learning based object detection algorithms to develop generic models with high detection performance for any SAR sensor and background condition. |
| first_indexed | 2024-03-11T18:31:08Z |
| format | Article |
| id | doaj.art-9e7a29271fd145a9851080cb4b3f60be |
| institution | Directory Open Access Journal |
| issn | 2352-3409 |
| language | English |
| last_indexed | 2024-03-11T18:31:08Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Data in Brief |
| spelling | doaj.art-9e7a29271fd145a9851080cb4b3f60be2023-10-13T11:04:51ZengElsevierData in Brief2352-34092023-10-0150109505iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applicationsMuhammad Farhan Humayun0Farrukh Aziz Bhatti1Khurram Khurshid2Corresponding author; iVision Lab, Department of Electrical Engineering, Institute of Space Technology, Islamabad, PakistaniVision Lab, Department of Electrical Engineering, Institute of Space Technology, Islamabad, PakistaniVision Lab, Department of Electrical Engineering, Institute of Space Technology, Islamabad, PakistanThis article describes a comprehensive Synthetic Aperture Radar (SAR) satellite based ships dataset for use in state of the art object detection algorithms. The dataset comprises 11,590 image tiles containing 27,885 ships examples. Each image tile has spatial dimensions of 512 × 512 pixels and is exported in JPEG format. The dataset contains a wide variety of inshore and offshore scenes under varying background settings and sea conditions to generate an all-inclusive understanding of the ship detection task in SAR satellite images. The dataset is generated using images from six different satellite sensors covering a wide range of electromagnetic spectrum including C, L and X band radar imaging frequencies. All the sensors have different resolutions and imaging modes. The dataset is randomly distributed into training, validation and test sets in the ratio of 70:20:10, respectively, for ease of comparison and bench-marking. The dataset was conceptualized, processed, labeled and verified at the Artificial Intelligence and Computer Vision (iVision) Lab at the Institute of Space Technology, Pakistan. To the best of our knowledge, this is the most diverse satellite based SAR ships dataset available in the public domain in terms of satellite sensors, radar imaging frequencies and background settings. The dataset can be used to train and optimize deep learning based object detection algorithms to develop generic models with high detection performance for any SAR sensor and background condition.http://www.sciencedirect.com/science/article/pii/S2352340923006054Ship detectionLocalizationSynthetic aperture radar (SAR)Multi resolution satellite imagesYOLO Labels formatShips dataset |
| spellingShingle | Muhammad Farhan Humayun Farrukh Aziz Bhatti Khurram Khurshid iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applications Data in Brief Ship detection Localization Synthetic aperture radar (SAR) Multi resolution satellite images YOLO Labels format Ships dataset |
| title | iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applications |
| title_full | iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applications |
| title_fullStr | iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applications |
| title_full_unstemmed | iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applications |
| title_short | iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applications |
| title_sort | ivision mrssd a comprehensive multi resolution sar ship detection dataset for state of the art satellite based maritime surveillance applications |
| topic | Ship detection Localization Synthetic aperture radar (SAR) Multi resolution satellite images YOLO Labels format Ships dataset |
| url | http://www.sciencedirect.com/science/article/pii/S2352340923006054 |
| work_keys_str_mv | AT muhammadfarhanhumayun ivisionmrssdacomprehensivemultiresolutionsarshipdetectiondatasetforstateoftheartsatellitebasedmaritimesurveillanceapplications AT farrukhazizbhatti ivisionmrssdacomprehensivemultiresolutionsarshipdetectiondatasetforstateoftheartsatellitebasedmaritimesurveillanceapplications AT khurramkhurshid ivisionmrssdacomprehensivemultiresolutionsarshipdetectiondatasetforstateoftheartsatellitebasedmaritimesurveillanceapplications |