SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson Bay
Remote sensing satellites have been broadly applied to sea ice monitoring. The substantial increase in satellite imagery provides a large amount of data support for deep learning methods in the sea ice classification field. However, there is a lack of public remote sensing datasets to facilitate sea...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/1/168 |
| _version_ | 1797497684915912704 |
|---|---|
| author | Wei Song Wen Gao Qi He Antonio Liotta Weiqi Guo |
| author_facet | Wei Song Wen Gao Qi He Antonio Liotta Weiqi Guo |
| author_sort | Wei Song |
| collection | DOAJ |
| description | Remote sensing satellites have been broadly applied to sea ice monitoring. The substantial increase in satellite imagery provides a large amount of data support for deep learning methods in the sea ice classification field. However, there is a lack of public remote sensing datasets to facilitate sea ice classification with spatial and temporal information and to benchmark the deep learning methods. In this paper, we provide a labeled large sea ice dataset derived from time-series sentinel-1 SAR images, dubbed SI-STSAR-7, and a validated dataset construction method for sea ice classification research. The SI-STSAR-7 dataset includes seven different sea ice types corresponding to different sea ice development stages in Hudson Bay during winter, and its samples are time sequences of SAR image patches in order to embody the differences of backscattering intensity and textures between different sea ice types, as well as the change of sea ice with time. We construct the dataset by first performing noise reduction and mitigation of incidence angle dependence on SAR images, and then producing data samples and labeling them based on our proposed sample-producing principles and the weekly regional ice charts provided by Canadian Ice Service. Three baseline classification methods are developed on SI-STSAR-7 to establish benchmarks, which are evaluated with accuracy and kappa coefficient. The sample-producing principles are verified through experiments. Based on the experimental results, sea ice classification can be implemented well on SI-STSAR-7. |
| first_indexed | 2024-03-10T03:22:45Z |
| format | Article |
| id | doaj.art-15c9664d28424431991d9a575cbbc8e0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:22:45Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-15c9664d28424431991d9a575cbbc8e02023-11-23T12:14:11ZengMDPI AGRemote Sensing2072-42922021-12-0114116810.3390/rs14010168SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson BayWei Song0Wen Gao1Qi He2Antonio Liotta3Weiqi Guo4College of Information Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Information Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Information Technology, Shanghai Ocean University, Shanghai 201306, ChinaFaculty of Computer Science, Free University of Bozen-Bolzano, 39100 Bolzano, ItalyShanghai East Sea Marine Engineering Survey and Design Institute Co., Ltd., Shanghai 200137, ChinaRemote sensing satellites have been broadly applied to sea ice monitoring. The substantial increase in satellite imagery provides a large amount of data support for deep learning methods in the sea ice classification field. However, there is a lack of public remote sensing datasets to facilitate sea ice classification with spatial and temporal information and to benchmark the deep learning methods. In this paper, we provide a labeled large sea ice dataset derived from time-series sentinel-1 SAR images, dubbed SI-STSAR-7, and a validated dataset construction method for sea ice classification research. The SI-STSAR-7 dataset includes seven different sea ice types corresponding to different sea ice development stages in Hudson Bay during winter, and its samples are time sequences of SAR image patches in order to embody the differences of backscattering intensity and textures between different sea ice types, as well as the change of sea ice with time. We construct the dataset by first performing noise reduction and mitigation of incidence angle dependence on SAR images, and then producing data samples and labeling them based on our proposed sample-producing principles and the weekly regional ice charts provided by Canadian Ice Service. Three baseline classification methods are developed on SI-STSAR-7 to establish benchmarks, which are evaluated with accuracy and kappa coefficient. The sample-producing principles are verified through experiments. Based on the experimental results, sea ice classification can be implemented well on SI-STSAR-7.https://www.mdpi.com/2072-4292/14/1/168open datasetsea ice classificationspatial and temporal informationSentinel-1 satellitedeep learningdataset construction |
| spellingShingle | Wei Song Wen Gao Qi He Antonio Liotta Weiqi Guo SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson Bay Remote Sensing open dataset sea ice classification spatial and temporal information Sentinel-1 satellite deep learning dataset construction |
| title | SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson Bay |
| title_full | SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson Bay |
| title_fullStr | SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson Bay |
| title_full_unstemmed | SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson Bay |
| title_short | SI-STSAR-7: A Large SAR Images Dataset with Spatial and Temporal Information for Classification of Winter Sea Ice in Hudson Bay |
| title_sort | si stsar 7 a large sar images dataset with spatial and temporal information for classification of winter sea ice in hudson bay |
| topic | open dataset sea ice classification spatial and temporal information Sentinel-1 satellite deep learning dataset construction |
| url | https://www.mdpi.com/2072-4292/14/1/168 |
| work_keys_str_mv | AT weisong sistsar7alargesarimagesdatasetwithspatialandtemporalinformationforclassificationofwinterseaiceinhudsonbay AT wengao sistsar7alargesarimagesdatasetwithspatialandtemporalinformationforclassificationofwinterseaiceinhudsonbay AT qihe sistsar7alargesarimagesdatasetwithspatialandtemporalinformationforclassificationofwinterseaiceinhudsonbay AT antonioliotta sistsar7alargesarimagesdatasetwithspatialandtemporalinformationforclassificationofwinterseaiceinhudsonbay AT weiqiguo sistsar7alargesarimagesdatasetwithspatialandtemporalinformationforclassificationofwinterseaiceinhudsonbay |