A new multi-source remote sensing image sample dataset with high resolution for flood area extraction: GF-FloodNet
Deep learning algorithms show good prospects for remote sensing flood monitoring. They mostly rely on huge amounts of labeled data. However, there is a lack of available labeled data in actual needs. In this paper, we propose a high-resolution multi-source remote sensing dataset for flood area extra...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17538947.2023.2230978 |
| _version_ | 1827811041473462272 |
|---|---|
| author | Yuwei Zhang Peng Liu Lajiao Chen Mengzhen Xu Xingyan Guo Lingjun Zhao |
| author_facet | Yuwei Zhang Peng Liu Lajiao Chen Mengzhen Xu Xingyan Guo Lingjun Zhao |
| author_sort | Yuwei Zhang |
| collection | DOAJ |
| description | Deep learning algorithms show good prospects for remote sensing flood monitoring. They mostly rely on huge amounts of labeled data. However, there is a lack of available labeled data in actual needs. In this paper, we propose a high-resolution multi-source remote sensing dataset for flood area extraction: GF-FloodNet. GF-FloodNet contains 13388 samples from Gaofen-3 (GF-3) and Gaofen-2 (GF-2) images. We use a multi-level sample selection and interactive annotation strategy based on active learning to construct it. Compare with other flood-related datasets, GF-FloodNet not only has a spatial resolution of up to 1.5 m and provides pixel-level labels, but also consists of multi-source remote sensing data. We thoroughly validate and evaluate the dataset using several deep learning models, including quantitative analysis, qualitative analysis, and validation on large-scale remote sensing data in real scenes. Experimental results reveal that GF-FloodNet has significant advantages by multi-source data. It can support different deep learning models for training to extract flood areas. There should be a potential optimal boundary for model training in any deep learning dataset. The boundary seems close to 4824 samples in GF-FloodNet. We provide GF-FloodNet at https://www.kaggle.com/datasets/pengliuair/gf-floodnet and https://pan.baidu.com/s/1vdUCGNAfFwG5UjZ9RLLFMQ?pwd=8v6o. |
| first_indexed | 2024-03-11T22:59:52Z |
| format | Article |
| id | doaj.art-b9bbd9a97ebb422e9f6aee429e9bba14 |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-11T22:59:52Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-b9bbd9a97ebb422e9f6aee429e9bba142023-09-21T15:09:03ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552023-12-011612522255410.1080/17538947.2023.22309782230978A new multi-source remote sensing image sample dataset with high resolution for flood area extraction: GF-FloodNetYuwei Zhang0Peng Liu1Lajiao Chen2Mengzhen Xu3Xingyan Guo4Lingjun Zhao5Aerospace Information Research InstituteAerospace Information Research InstituteAerospace Information Research InstituteTsinghua UniversityTsinghua UniversityAerospace Information Research InstituteDeep learning algorithms show good prospects for remote sensing flood monitoring. They mostly rely on huge amounts of labeled data. However, there is a lack of available labeled data in actual needs. In this paper, we propose a high-resolution multi-source remote sensing dataset for flood area extraction: GF-FloodNet. GF-FloodNet contains 13388 samples from Gaofen-3 (GF-3) and Gaofen-2 (GF-2) images. We use a multi-level sample selection and interactive annotation strategy based on active learning to construct it. Compare with other flood-related datasets, GF-FloodNet not only has a spatial resolution of up to 1.5 m and provides pixel-level labels, but also consists of multi-source remote sensing data. We thoroughly validate and evaluate the dataset using several deep learning models, including quantitative analysis, qualitative analysis, and validation on large-scale remote sensing data in real scenes. Experimental results reveal that GF-FloodNet has significant advantages by multi-source data. It can support different deep learning models for training to extract flood areas. There should be a potential optimal boundary for model training in any deep learning dataset. The boundary seems close to 4824 samples in GF-FloodNet. We provide GF-FloodNet at https://www.kaggle.com/datasets/pengliuair/gf-floodnet and https://pan.baidu.com/s/1vdUCGNAfFwG5UjZ9RLLFMQ?pwd=8v6o.http://dx.doi.org/10.1080/17538947.2023.2230978flood area extractiondataset constructionmulti-source remote sensing datadeep learning |
| spellingShingle | Yuwei Zhang Peng Liu Lajiao Chen Mengzhen Xu Xingyan Guo Lingjun Zhao A new multi-source remote sensing image sample dataset with high resolution for flood area extraction: GF-FloodNet International Journal of Digital Earth flood area extraction dataset construction multi-source remote sensing data deep learning |
| title | A new multi-source remote sensing image sample dataset with high resolution for flood area extraction: GF-FloodNet |
| title_full | A new multi-source remote sensing image sample dataset with high resolution for flood area extraction: GF-FloodNet |
| title_fullStr | A new multi-source remote sensing image sample dataset with high resolution for flood area extraction: GF-FloodNet |
| title_full_unstemmed | A new multi-source remote sensing image sample dataset with high resolution for flood area extraction: GF-FloodNet |
| title_short | A new multi-source remote sensing image sample dataset with high resolution for flood area extraction: GF-FloodNet |
| title_sort | new multi source remote sensing image sample dataset with high resolution for flood area extraction gf floodnet |
| topic | flood area extraction dataset construction multi-source remote sensing data deep learning |
| url | http://dx.doi.org/10.1080/17538947.2023.2230978 |
| work_keys_str_mv | AT yuweizhang anewmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT pengliu anewmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT lajiaochen anewmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT mengzhenxu anewmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT xingyanguo anewmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT lingjunzhao anewmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT yuweizhang newmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT pengliu newmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT lajiaochen newmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT mengzhenxu newmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT xingyanguo newmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet AT lingjunzhao newmultisourceremotesensingimagesampledatasetwithhighresolutionforfloodareaextractiongffloodnet |