└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Benchmarks-for-Water-Body-Extraction-from-High-Resolution-Optical-RS-Imagery 2 | ---- 3 | ## Paper 4 | - Title: Water body classification from high-resolution optical remote sensing imagery: Achievements and perspectives. 5 | - DOI: https://doi.org/10.1016/j.isprsjprs.2022.03.013 6 | 7 |
8 | 9 | ---- 10 | 11 | ## Benchmarks 12 | To facilitate the qualitative and quantitative comparison in the research avenue, the two benchmarks employed in our paper and links to other relevant datasets and open-source codes will be summarized and released in this repository. 13 | 14 | **No.1 Gaofen Image Dataset (GID)** 15 | 16 | - Introduction: The GID was proposed in 2018 by a group from Wuhan University and contains 5 or 15 classes originally. In total, this dataset includes 10 fine land cover images and annotations, and 150 large-scale images and annotations. They are all captured from the GF-2 satellite and the pixel resolution is 4 m. we select representative samples and crop them to small samples with the size of 256 × 256, of which the total images number is 19500. 60% are used for training, 20% and 20% are used for validation and testing, respectively. 17 | - The benchmark can be download from Baidudrive: 18 | - Link: [Baidudrive][gid] (extraction code: ae4y) 19 | - Copyright Announcement：Please consider citing as follows: 20 | 21 | ``` 22 | @article{tong2020land, 23 | title={Land-cover classification with high-resolution remote sensing images using transferable deep models}, 24 | author={Tong, Xin-Yi and Xia, Gui-Song and Lu, Qikai and Shen, Huanfeng and Li, Shengyang and You, Shucheng and Zhang, Liangpei}, 25 | journal={Remote Sensing of Environment}, 26 | volume={237}, 27 | pages={111322}, 28 | year={2020}, 29 | publisher={Elsevier} 30 | } 31 | ``` 32 | 33 | **No.2 2020 Gaofen challenge water body segmentation dataset** 34 | 35 | - Introduction: The 2020 Gaofen challenge water body segmentation dataset was released by the 2020 Gaofen Challenge committee, which is the current only specific high-resolution optical dataset for water body classification. The dataset contains 1000 RGB images from the GF-2 satellite, of which the pixel resolution is ranging from 1 to 4 m. 36 | - The benchmark can be download from Baidudrive: 37 | - Link: [Baidudrive][gf] (extraction code: jo56) 38 | - Copyright Announcement：Please consider citing as follows: 39 | 40 | ``` 41 | @article{sun2021automated, 42 | title={Automated High-Resolution Earth Observation Image Interpretation: Outcome of the 2020 Gaofen Challenge}, 43 | author={Sun, Xian and Wang, Peijin and Yan, Zhiyuan and Diao, Wenhui and Lu, Xiaonan and Yang, Zhujun and Zhang, Yidan and Xiang, Deliang and Yan, Chen and Guo, Jie and others}, 44 | journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, 45 | volume={14}, 46 | pages={8922--8940}, 47 | year={2021}, 48 | publisher={IEEE} 49 | } 50 | ``` 51 | ## Relevant information 52 | **:one: Other relevant datasets（:white_check_mark: Last updated on March 18, 2023)** 53 | 54 | Datasets | Total image number | Image bands number | Image size (pixels) | Spatial resolution | Data sources | Year | Link 55 | :----: | :----: | :----: | :----: | :----: | :----: | :----: | :----: 56 | Zurich Summer | 20 | 4 | 600∼1600 × 600∼1600 | 0.62m | QuickBird | 2015 | [Zurich Summer][Zurich Summer] 57 | WHDLD | 4940 | 3 | 256 × 256 | 2m | GF-1 & ZY-3 | 2018 | [WHDLD][WHDLD] 58 | DLRSD | 2100 | 3 | 256 × 256 | 0.3m | UC Merced archive | 2018 | [DLRSD][DLRSD] 59 | DeepGlobe | 803 | 3 | 2448 × 2448 | 0.5m | DigitalGlobe | 2018 | [DeepGlobe][DeepGlobe] 60 | GID | 10/150 | 3/4 | 7200 × 6800 | 4m | GF-2 | 2018 | [GID][GID] 61 | DroneDeploy | 55 | 3 | 6000 × 6000 | 0.1m | Aerial images | 2019 | [DroneDeploy][DroneDeploy] 62 | EORSSD | 2000 | 3 | 500 × 500 | - | Google Earth | 2020 | [EORSSD][EORSSD] 63 | Landcover_ai | 41 | 3 | 9000 × 9500/4200 × 4700 | 0.25m/0.5m | Public Geodetic Resource | 2020 | [Landcover_ai][Landcover_ai] 64 | 2020 Gaofen Challenge dataset | 1000/2500 | 3 | 492∼2000 × 492∼2000 | 1 to 4m | GF-2 | 2020 | [GF-water][GF-water] 65 | LoveDA | 5987 | 3 | 1024 × 1024 | 0.3m | Google Earth | 2021 | [LoveDA][LoveDA] 66 | Five-Billion-Pixels | 150 | 4 | 7200 × 6800 | 4m | GF-2 | 2022 | [FBP][FBP] 67 | Urban Watch | 200 | 4 | 512 × 512 | 1m | NAIP | 2022 | [Urban Watch][Urban Watch] 68 | DynamicEarthNet | 54750 | 4 | 1024 × 1024 | 3 | PlanetFusion | 2022 | [DynamicEarthNet][DynamicEarthNet] 69 | Satlas | 496468 | 4/6 | 512 × 512 | 1/10 | NAIP/Sentinel-2 | 2022 | [Satlas][Satlas] 70 | OpenEarthMap | 5000 | 3 | 1024 × 1024 | 0.25-0.5 | - | 2023 | [OpenEarthMap][OpenEarthMap] 71 | GLH-water | 250 | 3 | 12800 × 12800 | 0.3 | Google Earth | 2023 | [GLH-water][GLH-water] 72 | 73 | **:two: Summary of existing reviews of water body classification（:white_check_mark: Last updated on March 30, 2022)** 74 | No. | Review title | Year | Publication | DOI/URL 75 | :----: | :----: | :----: | :----: | :----: 76 | 1 | A review of hyperspectral remote sensing and its applicationin vegetation and water resource studies | 2007 | Water Sa | https://journals.co.za/doi/abs/10.10520/EJC116430 77 | 2 | Water-body area extraction from high resolution satellite images-an introduction, review, and comparison | 2010 | IJIP | http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.301.8033&rep=rep1&type=pdf 78 | 3 | Water body extraction methods study based on RS and GIS | 2011 | PROENV | https://doi.org/10.1016/j.proenv.2011.09.407 79 | 4 | A review on extraction of lakes from remotely sensed optical satellite data with a special focus on cryospheric lakes | 2015 | ARS | https://doi.org/10.4236/ars.2015.43016 80 | 5 | A review of applications of satellite SAR, optical, altimetry and DEM data for surface water modelling, mapping and parameter estimation | 2015 | HESS | https://hess.copernicus.org/articles/19/3755/2015/hess-19-3755-2015.pdf 81 | 6 | Detecting, extracting, and monitoring surface water from space using optical sensors: A review | 2018 | REV GEOPHYS | https://doi.org/10.1029/2018RG000598 82 | 7 | A review on applications of remote sensing and geographic information systems (GIS) in water resources and flood risk management | 2018 | Water | https://doi.org/10.3390/w10050608 83 | 8 | Evaluation of water indices for surface water extraction in a Landsat 8 scene of Nepal | 2018 | Sensors | https://doi.org/10.3390/s18082580 84 | 9 | Inundation extent mapping by synthetic aperture radar: A review | 2019 | Remote Sensing | https://doi.org/10.3390/rs11070879 85 | 10 | Surface water detection and delineation using remote sensing images: A review of methods and algorithms | 2020 | SWAM | https://link.springer.com/content/pdf/10.1007/s40899-020-00425-4.pdf 86 | 11 | A comprehensive review of deep learning applications in hydrology and water resources | 2020 | Water Sci Technol | https://doi.org/10.2166/wst.2020.369 87 | 12 | Towards Synoptic Water Monitoring Systems: A Review of AI Methods for Automating Water Body Detection and Water Quality Monitoring Using Remote Sensing | 2022 | Sensors | https://doi.org/10.3390/s22062416 88 | 13 | Water body classification from high-resolution optical remote sensing imagery: Achievements and perspectives | 2022 | ISPRS JPRS | https://doi.org/10.1016/j.isprsjprs.2022.03.013 89 | 90 | **:three: Relevant open-source codes（:white_check_mark: Last updated on March 30, 2022)** 91 | 92 | - [Deepwatermap][Deepwatermap] 93 | - [NDWI][NDWI] 94 | - [WaterNet][WaterNet] 95 | - [MECNet][MECNet] 96 | - [MSResNet-via-SSL][MSResNet-via-SSL] 97 | - [WatNet][WatNet] 98 | - [WatNetv2][WatNetv2] 99 | 100 | **:four: Some latest papers/approaches not included in our paper（:white_check_mark: Last updated on March 30, 2022)** 101 | No. | Title | Category | Year | Publication | DOI/URL 102 | :----: | :----: | :----: | :----: | :----: | :----: 103 | 1 | NFANet: A Novel Method for Weakly Supervised Water Extraction From High-Resolution Remote-Sensing Imagery | Weakly Supervised | 2022 | IEEE TGRS | https://doi.org/10.1109/TGRS.2022.3140323 104 | 2 | Multi-Scale Feature Aggregation Network for Water Area Segmentation | Feature fusion-based | 2022 | Remote Sensing | https://doi.org/10.3390/rs14010206 105 | 3 | SADA-Net: A Shape Feature Optimization and Multiscale Context Information-Based Water Body Extraction Method for High-Resolution Remote Sensing Images | - | 2022 | IEEE J-STARS | https://doi.org/10.1109/JSTARS.2022.3146275 106 | 107 | ## Citation 108 | 109 | If our work has any help to you, please cite as follows: 110 | 111 | ``` 112 | @article{li2022water, 113 | title={Water body classification from high-resolution optical remote sensing imagery: Achievements and perspectives}, 114 | author={Li, Yansheng and Dang, Bo and Zhang, Yongjun and Du, Zhenhong}, 115 | journal={ISPRS Journal of Photogrammetry and Remote Sensing}, 116 | volume={187}, 117 | pages={306--327}, 118 | year={2022}, 119 | publisher={Elsevier} 120 | } 121 | ``` 122 | 123 | ## Contact 124 | 125 | If you have any questions about it, please feel free to let me know. (:email: email:bodang@whu.edu.cn) 126 | 127 | 128 | ******************* 129 | [gid]:https://pan.baidu.com/s/1f7yd8B_Y8nl3Za8zl7KI0Q 130 | [gf]:https://pan.baidu.com/s/1HMvZC933f3xgNr6vrDHSzg 131 | [Zurich Summer]:https://sites.google.com/site/michelevolpiresearch/data/zurich-dataset 132 | [WHDLD]:https://sites.google.com/view/zhouwx/dataset#h.p_hQS2jYeaFpV0 133 | [DLRSD]:https://sites.google.com/view/zhouwx/dataset#h.p_hQS2jYeaFpV0 134 | [DeepGlobe]:http://deepglobe.org/challenge.html 135 | [GID]:https://captain-whu.github.io/GID15/ 136 | [DroneDeploy]:https://github.com/dronedeploy/dd-ml-segmentation-benchmark 137 | [EORSSD]:https://hub.fastgit.org/rmcong/EORSSD-dataset 138 | [Landcover_ai]:https://landcover.ai/ 139 | [GF-water]:https://github.com/AICyberTeam/2020Gaofen 140 | [LoveDA]:https://github.com/Junjue-Wang/LoveDA 141 | [FBP]:https://x-ytong.github.io/project/Five-Billion-Pixels.html 142 | [Urban Watch]:https://urbanwatch.charlotte.edu 143 | [DynamicEarthNet]:https://mediatum.ub.tum.de/1650201 144 | [Satlas]:https://satlas.apps.allenai.org/ 145 | [OpenEarthMap]:https://open-earth-map.org/ 146 | [GLH-water]:https://jack-bo1220.github.io/project/GLH-water.html 147 | [Deepwatermap]:https://github.com/isikdogan/deepwatermap 148 | [MSResNet-via-SSL]: https://github.com/Jack-bo1220/MSResNet-via-SSL 149 | [MECNet]: https://github.com/ZhangZhily/MECNet 150 | [WaterNet]:https://github.com/treigerm/WaterNet 151 | [WatNet]:https://github.com/xinluo2018/WatNet 152 | [WatNetv2]:https://github.com/xinluo2018/WatNetv2 153 | [NDWI]:https://github.com/Whu-yla/NDWI-Project 154 | --------------------------------------------------------------------------------