Automatic Ship Recognition Chain on Satellite Multispectral Imagery
This article elaborates a processing chain devised to recognize the ships existing on medium resolution multispectral imageries (MSI). The chain consists of the following three steps. Firstly, an adaptive local saliency mapping technique is instigated on open ocean regions to obtain all floating obj...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9281035/ |
| _version_ | 1819274998548791296 |
|---|---|
| author | Kamirul Kamirul Wahyudi Hasbi Patria Rachman Hakim A. Hadi Syafrudin |
| author_facet | Kamirul Kamirul Wahyudi Hasbi Patria Rachman Hakim A. Hadi Syafrudin |
| author_sort | Kamirul Kamirul |
| collection | DOAJ |
| description | This article elaborates a processing chain devised to recognize the ships existing on medium resolution multispectral imageries (MSI). The chain consists of the following three steps. Firstly, an adaptive local saliency mapping technique is instigated on open ocean regions to obtain all floating objects. Secondly, to extract the ship candidates, two-step verification is applied based on specific spectral and geometric information of the ships. Lastly, a calculation to determine the properties of the ships, including their length, breadth, and heading, is then carried out. Furthermore, we propose a novel method for correcting miscalculated ship heading; by combining wake segmentation and Radon Transform (RT) approaches to locate the position and estimate the length of the wake generated by the ships. With the detected wake length, ship velocity can also be assessed. The developed chain is then tested using imageries acquired by LAPAN-A3 microsatellite, and the results are compared to those reported by the Automatic Identification System (AIS). Experimental results indicate that the proposed chain achieves higher detection performance and can produce better heading information compared to the existing methods. |
| first_indexed | 2024-12-23T23:17:20Z |
| format | Article |
| id | doaj.art-89af7d05ee9446e59ed9166b7625379b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-23T23:17:20Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-89af7d05ee9446e59ed9166b7625379b2022-12-21T17:26:28ZengIEEEIEEE Access2169-35362020-01-01822191822193110.1109/ACCESS.2020.30427029281035Automatic Ship Recognition Chain on Satellite Multispectral ImageryKamirul Kamirul0https://orcid.org/0000-0002-1474-1139Wahyudi Hasbi1https://orcid.org/0000-0001-5616-3683Patria Rachman Hakim2A. Hadi Syafrudin3Satellite Control, Space and Atmospheric Observation, and Remote Sensing Office, National Institute of Aeronautics and Space, Biak, IndonesiaSatellite Technology Center, National Institute of Aeronautics and Space, Bogor, IndonesiaSatellite Technology Center, National Institute of Aeronautics and Space, Bogor, IndonesiaSatellite Technology Center, National Institute of Aeronautics and Space, Bogor, IndonesiaThis article elaborates a processing chain devised to recognize the ships existing on medium resolution multispectral imageries (MSI). The chain consists of the following three steps. Firstly, an adaptive local saliency mapping technique is instigated on open ocean regions to obtain all floating objects. Secondly, to extract the ship candidates, two-step verification is applied based on specific spectral and geometric information of the ships. Lastly, a calculation to determine the properties of the ships, including their length, breadth, and heading, is then carried out. Furthermore, we propose a novel method for correcting miscalculated ship heading; by combining wake segmentation and Radon Transform (RT) approaches to locate the position and estimate the length of the wake generated by the ships. With the detected wake length, ship velocity can also be assessed. The developed chain is then tested using imageries acquired by LAPAN-A3 microsatellite, and the results are compared to those reported by the Automatic Identification System (AIS). Experimental results indicate that the proposed chain achieves higher detection performance and can produce better heading information compared to the existing methods.https://ieeexplore.ieee.org/document/9281035/LAPAN-A3satellitemedium resolutionrecognitionremote sensingship |
| spellingShingle | Kamirul Kamirul Wahyudi Hasbi Patria Rachman Hakim A. Hadi Syafrudin Automatic Ship Recognition Chain on Satellite Multispectral Imagery IEEE Access LAPAN-A3 satellite medium resolution recognition remote sensing ship |
| title | Automatic Ship Recognition Chain on Satellite Multispectral Imagery |
| title_full | Automatic Ship Recognition Chain on Satellite Multispectral Imagery |
| title_fullStr | Automatic Ship Recognition Chain on Satellite Multispectral Imagery |
| title_full_unstemmed | Automatic Ship Recognition Chain on Satellite Multispectral Imagery |
| title_short | Automatic Ship Recognition Chain on Satellite Multispectral Imagery |
| title_sort | automatic ship recognition chain on satellite multispectral imagery |
| topic | LAPAN-A3 satellite medium resolution recognition remote sensing ship |
| url | https://ieeexplore.ieee.org/document/9281035/ |
| work_keys_str_mv | AT kamirulkamirul automaticshiprecognitionchainonsatellitemultispectralimagery AT wahyudihasbi automaticshiprecognitionchainonsatellitemultispectralimagery AT patriarachmanhakim automaticshiprecognitionchainonsatellitemultispectralimagery AT ahadisyafrudin automaticshiprecognitionchainonsatellitemultispectralimagery |