DaliWS: A High-Resolution Dataset with Precise Annotations for Water Segmentation in Synthetic Aperture Radar Images
The frequent occurrence of global flood disasters leads to millions of people falling into poverty each year, which poses immense pressure on governments and hinders social development. Therefore, providing more data support for flood disaster detection is of paramount importance. To facilitate the...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/4/720 |
| _version_ | 1797297082737885184 |
|---|---|
| author | Shanshan Zhang Weibin Li Rongfang Wang Chenbin Liang Xihui Feng Yanhua Hu |
| author_facet | Shanshan Zhang Weibin Li Rongfang Wang Chenbin Liang Xihui Feng Yanhua Hu |
| author_sort | Shanshan Zhang |
| collection | DOAJ |
| description | The frequent occurrence of global flood disasters leads to millions of people falling into poverty each year, which poses immense pressure on governments and hinders social development. Therefore, providing more data support for flood disaster detection is of paramount importance. To facilitate the development of water body detection algorithms, we create the DaliWS dataset for water segmentation, which contains abundant pixel-level annotations, and consists of high spatial resolution SAR images collected from the GaoFen-3 (GF-3) satellite. For comprehensive analysis, extensive experiments are conducted on the DaliWS dataset to explore the performance of the state-of-the-art segmentation models, including FCN, SegNeXt, U-Net, and DeeplabV3+, and investigate the impact of different polarization modes on water segmentation. Additionally, to probe the generalization of our dataset, we further evaluate the models trained with the DaliWS dataset, on publicly available water segmentation datasets. Through detailed analysis of the experimental results, we establish a valuable benchmark and provide usage guidelines for future researchers working with the DaliWS dataset. The experimental results demonstrate the F1 scores of FCN, SegNeXt, U-Net, and DeeplabV3+ on the dual-polarization data of DaliWS dataset reach to 90.361%, 90.192%, 92.110%, and 91.199%, respectively, and these four models trained using the DaliWS dataset exhibit excellent generalization performance on the public dataset, which further confirms the research value of our dataset. |
| first_indexed | 2024-03-07T22:15:07Z |
| format | Article |
| id | doaj.art-950d4b91bfc94e33a25d74c1f4385ef3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-07T22:15:07Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-950d4b91bfc94e33a25d74c1f4385ef32024-02-23T15:33:12ZengMDPI AGRemote Sensing2072-42922024-02-0116472010.3390/rs16040720DaliWS: A High-Resolution Dataset with Precise Annotations for Water Segmentation in Synthetic Aperture Radar ImagesShanshan Zhang0Weibin Li1Rongfang Wang2Chenbin Liang3Xihui Feng4Yanhua Hu5School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaLaboratory of Artificial Intelligence, Hangzhou Institute of Technology of Xidian University, Hangzhou 311231, ChinaKey Laboratory of Coal Resources Exploration and Comprehensive Utilization, Ministry of Natural Resources, Xi’an 710021, ChinaDepartment of Water Resources of Shaanxi Province, Xi’an 710004, ChinaThe frequent occurrence of global flood disasters leads to millions of people falling into poverty each year, which poses immense pressure on governments and hinders social development. Therefore, providing more data support for flood disaster detection is of paramount importance. To facilitate the development of water body detection algorithms, we create the DaliWS dataset for water segmentation, which contains abundant pixel-level annotations, and consists of high spatial resolution SAR images collected from the GaoFen-3 (GF-3) satellite. For comprehensive analysis, extensive experiments are conducted on the DaliWS dataset to explore the performance of the state-of-the-art segmentation models, including FCN, SegNeXt, U-Net, and DeeplabV3+, and investigate the impact of different polarization modes on water segmentation. Additionally, to probe the generalization of our dataset, we further evaluate the models trained with the DaliWS dataset, on publicly available water segmentation datasets. Through detailed analysis of the experimental results, we establish a valuable benchmark and provide usage guidelines for future researchers working with the DaliWS dataset. The experimental results demonstrate the F1 scores of FCN, SegNeXt, U-Net, and DeeplabV3+ on the dual-polarization data of DaliWS dataset reach to 90.361%, 90.192%, 92.110%, and 91.199%, respectively, and these four models trained using the DaliWS dataset exhibit excellent generalization performance on the public dataset, which further confirms the research value of our dataset.https://www.mdpi.com/2072-4292/16/4/720dataset constructionwater segmentationsynthetic aperture radardeep learningGF-3 |
| spellingShingle | Shanshan Zhang Weibin Li Rongfang Wang Chenbin Liang Xihui Feng Yanhua Hu DaliWS: A High-Resolution Dataset with Precise Annotations for Water Segmentation in Synthetic Aperture Radar Images Remote Sensing dataset construction water segmentation synthetic aperture radar deep learning GF-3 |
| title | DaliWS: A High-Resolution Dataset with Precise Annotations for Water Segmentation in Synthetic Aperture Radar Images |
| title_full | DaliWS: A High-Resolution Dataset with Precise Annotations for Water Segmentation in Synthetic Aperture Radar Images |
| title_fullStr | DaliWS: A High-Resolution Dataset with Precise Annotations for Water Segmentation in Synthetic Aperture Radar Images |
| title_full_unstemmed | DaliWS: A High-Resolution Dataset with Precise Annotations for Water Segmentation in Synthetic Aperture Radar Images |
| title_short | DaliWS: A High-Resolution Dataset with Precise Annotations for Water Segmentation in Synthetic Aperture Radar Images |
| title_sort | daliws a high resolution dataset with precise annotations for water segmentation in synthetic aperture radar images |
| topic | dataset construction water segmentation synthetic aperture radar deep learning GF-3 |
| url | https://www.mdpi.com/2072-4292/16/4/720 |
| work_keys_str_mv | AT shanshanzhang daliwsahighresolutiondatasetwithpreciseannotationsforwatersegmentationinsyntheticapertureradarimages AT weibinli daliwsahighresolutiondatasetwithpreciseannotationsforwatersegmentationinsyntheticapertureradarimages AT rongfangwang daliwsahighresolutiondatasetwithpreciseannotationsforwatersegmentationinsyntheticapertureradarimages AT chenbinliang daliwsahighresolutiondatasetwithpreciseannotationsforwatersegmentationinsyntheticapertureradarimages AT xihuifeng daliwsahighresolutiondatasetwithpreciseannotationsforwatersegmentationinsyntheticapertureradarimages AT yanhuahu daliwsahighresolutiondatasetwithpreciseannotationsforwatersegmentationinsyntheticapertureradarimages |