Please wait a minute...
 
Remote Sensing for Natural Resources    2022, Vol. 34 Issue (3) : 50-58     DOI: 10.6046/zrzyyg.2021227
|
The construction and verification of a water index in the complex environment based on GF-2 images
WANG Chunxia1(), ZHANG Jun1(), LI Yixu2, PHOUMILAY1
1. College of Mining, Guizhou University, Guiyang 550000, China
2. College of Agriculture, Guizhou University, Guiyang 550000, China
Download: PDF(6866 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

The high spatial resolution of GF-2 images helps to obtain more accurate water distribution information. This study constructed a water index based on GF-2 images and verified it, aiming to solve the problem that the salt and pepper noise is prone to occur when the existing water indices are used to extract information on water bodies in complex environments from high-resolution remote sensing images. Firstly, this study established a comprehensive water index (CWI) by analyzing the spectral information of surface coverings and verified its precision. Secondly, information on water bodies was extracted through image segmentation combined with the CWI, and the extraction precision was verified. Then, to fully utilize the spectral information and the advantages of a classifier, the spectral information on the segmented homogeneous objects and the CWI were combined as the input data of the classifier to extract information on water bodies and verify the extraction precision. Finally, this study verified the applicability of the CWI in both WorldView-2 and GF-1 images. The results are as follows. ① The newly constructed CWI can effectively suppress the impacts of surface coverings, such as shadow, buildings, roads, vegetation, and bare soil, thus significantly improving the extraction precision. ② Extracting information on water bodies through image segmentation combined with the CWI can effectively inhibit the occurrence of the pepper and salt noise. ③ A classifier combined with a water index can effectively improve the information extraction precision of water bodies. ④ The CWI is applicable to both WorldView-2 and GF-1 images. In sum, the CWI can be used to effectively extract information on water bodies and applies to the information extraction and renewal of rivers and lakes and the surveys of the cultivation area of pounds and thereby is a high-precision method for extraction information of water bodies.
Keywords information extraction of water bodies      comprehensive water index      GF-2      support vector machine      random forest     
ZTFLH:  TP79  
Corresponding Authors: ZHANG Jun     E-mail: 1821851037@qq.com;jzhang13@gzu.edu.cn
Issue Date: 21 September 2022
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Chunxia WANG
Jun ZHANG
Yixu LI
PHOUMILAY
Cite this article:   
Chunxia WANG,Jun ZHANG,Yixu LI, et al. The construction and verification of a water index in the complex environment based on GF-2 images[J]. Remote Sensing for Natural Resources, 2022, 34(3): 50-58.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2021227     OR     https://www.gtzyyg.com/EN/Y2022/V34/I3/50
Fig.1  Spectral curve of average reflectance of each surface feature
Fig.2  Distribution of water body index of various surface features
模型名称 计算公式① 来源
归一化差异植被指数 N D V I = ( ρ N I R - ρ R E D ) / ( ρ R E D + ρ N I R ) [27]
归一化差异水体指数 N D W I = ( ρ G R E E N - ρ N I R ) / ( ρ G R E E N + ρ N I R ) [15]
阴影水体指数 S W I = ρ B L U E + ρ G R E E N - ρ N I R [19]
改进的阴影水体指数 M S W I = ( ρ B L U E - ρ N I R ) / ρ N I R [6]
增强的阴影水体指数 E S W I = ( ρ B L U E + ρ G R E E N ) / ( 2 ρ N I R ) [28]
Tab.1  Common used water indexes
研究区 影像来源 地表覆盖特征
研究区1 GF-2 水体、植被、阴影、建筑物、裸土
研究区2 GF-2 水体、植被、高大建筑物阴影、山体阴影、建筑物、裸土、高反射建筑物
研究区3 WorldView-2 建筑物、池塘、裸土、阴影
研究区4 GF-1 水体、旱地、低反射地物、蓝色屋顶房屋
Tab.2  Characteristics of the study area
Fig.3  Results of water body extraction in site 1
评价指标 NDVI CWI SWI ESWI NDWI MSWI SVM RF
总体精度 99.65 99.95 90.15 99.34 99.66 95.93 99.62 99.75
Kappa系数 98.83 99.83 72.62 97.82 98.86 85.46 92.21 94.42
Tab.3  Results of accuracy assessment in site 1(%)
Fig.4  Results of water body extraction in site 2
Fig.5  Enlarged view in site 2
评价指标 NDVI CWI SVM RF NDWI SWI ESWI MSWI
总体精度 99.33 99.97 99.94 99.67 99.33 93.80 98.49 99.43
Kappa系数 45.31 94.86 90.70 63.14 45.31 0.08 0.26 49.18
Tab.4  Results of accuracy assessment in site 2(%)
分类方法 第一类数据 第二类数据 第三类数据
SVM
RF
Tab.5  Water extraction results of different data combinations
方法 评价指标 第一类数据 第二类数据 第三类数据
SVM 总体精度 99.98 99.98 99.98
Kappa系数 95.85 96.07 95.85
RF 总体精度 99.99 99.99 99.99
Kappa系数 98.44 98.78 98.17
Tab.6  Water extraction accuracy evaluation of different data combinations(%)
Fig.6  Result of water body extraction in Site 2
Fig.7  Results of water body extraction in site 3
评价指标 NDVI CWI NDWI SWI ESWI MSWI
总体精度 98.12 99.30 99.42 94.86 99.33 96.05
Kappa系数 85.46 94.62 95.66 70.53 94.97 75.83
Tab.7  Results of accuracy assessment in site 3(%)
Fig.8  Results of water body extraction in site 4
评价指标 NDVI CWI NDWI SWI ESWI MSWI
总体精度 74.37 100 78.71 78.37 80.93 80.93
Kappa系数 36.09 100 38.46 52.37 61.39 61.39
Tab.8  Results of accuracy assessment in site 4(%)
[1] Yang C J, Wei Y M, Wang S Y, et al. Extracting the flood extent from satellite SAR image with the support of topographic data[C]// International Conferences on Info-Tech and Info-Net.IEEE Computer Society, 1998.
[2] 何红术, 黄晓霞, 李红旮, 等. 基于改进U-Net网络的高分遥感影像水体提取[J]. 地球信息科学学报, 2020, 22(10):2010-2022.
doi: 10.12082/dqxxkx.2020.190622
[2] He H S, Huang X X, Li H G, et al. Water body extraction of high resolution remote sensing image basedon improved U-Net network[J]. Journal of Geo-Information Science, 2020, 22(10):2010-2022.
[3] 梁泽毓, 吴艳兰, 杨辉, 等. 基于密集连接全卷积神经网络的遥感影像水体全自动提取方法[J]. 遥感信息, 2020, 35(4):68-77.
[3] Liang Z Y, Wu Y L, Yang H, et al. Full-automatic water extraction method for remote sensing image based on densely connected full convolutional neural network[J]. Remote Sensing Information, 2020, 35(4):68-77
[4] 陈前, 郑利娟, 李小娟, 等. 基于深度学习的高分遥感影像水体提取模型研究[J]. 地理与地理信息科学, 2019, 35(4):43-49.
[4] Chen Q, Zheng L J, Li X J, et al. Water boby extraction form high-resolution satellite remote sensing images based on deep learning[J]. Geography and Geo-Information Science, 2019, 35(4):43-49.
[5] Gulcan S, Mehmet O. Water body extraction and change detection using time series: A case study of Lake Burdur,Turkey[J]. Journal of Taibah University for Science, 2017, 11(3):381-391.
doi: 10.1016/j.jtusci.2016.04.005 url: https://www.tandfonline.com/doi/full/10.1016/j.jtusci.2016.04.005
[6] 王瑾杰, 丁建丽, 张成, 等. 基于GF-1卫星影像的改进SWI水体提取方法[J]. 国土资源遥感, 2017, 29(1):29-35.doi: 10.6046/gtzyyg.2017.01.05.
doi: 10.6046/gtzyyg.2017.01.05
[6] Wang J J, Ding J L, Zhang C, et al. Method of water information extraction by improved SWI based on GF-1 satellite image[J]. Remote Sensing for Land and Resources, 2017, 29(1):29-35.doi: 10.6046/gtzyyg.2017.01.05.
doi: 10.6046/gtzyyg.2017.01.05
[7] 毛莹莹, 陈友飞. 基于面向对象法的Landsat8影像山区细小水体提取方法[J]. 亚热带资源与环境学报, 2015, 10(4):86-92.
[7] Mao Y Y, Chen Y F. Water body extraction method based on object-oriented in mountainous area with Landsat8 image[J]. Journal of Subtropical Resources and Environment, 2015, 10(4):86-92.
[8] 胡卫国, 孟令奎, 张东映, 等. 资源一号02C星图像水体信息提取方法[J]. 国土资源遥感, 2014, 26(2):43-47.doi: 10.6046/gtzyyg.2014.02.08.
doi: 10.6046/gtzyyg.2014.02.08
[8] Hu W G, Meng L K, Zhang D Y, et al. Method of water extraction from ZY-1 02C satellite image[J]. Remote Sensing for Land and Resources, 2014, 26(2):43-47.doi: 10.6046/gtzyyg.2014.02.08.
doi: 10.6046/gtzyyg.2014.02.08
[9] 王小标, 谢顺平, 都金康. 水体指数构建及其在复杂环境下有效性研究[J]. 遥感学报, 2018, 22(2):360-372.
[9] Wang X B, Xie S P, Du J K. Water index formulation and its effectiveness research on the complicated surface water surroundings[J]. Journal of Remote Sensing, 2018, 22(2): 360-372.
[10] 杨树文, 李轶鲲, 刘涛, 等. 基于SPOT5影像自动提取水体的新方法[J]. 武汉大学学报(信息科学版), 2015, 40(3):308-314.
[10] Yang S W, Li Y K, Liu T, et al. A new automatic water boby feature extraction method based on SPOT5 images[J]. Geomatics and Information Science of Wuhan University, 2015, 40(3):308-314.
[11] Gudina L F, Henrik M, Rasmus F, et al. Automated water extraction index:A new technique for surface water mapping using Landsat imagery[J]. Remote Sensing of Environment, 2014, 140(1):23-35.
doi: 10.1016/j.rse.2013.08.029 url: https://linkinghub.elsevier.com/retrieve/pii/S0034425713002873
[12] 沈占锋, 夏列钢, 李均力, 等. 采用高斯归一化水体指数实现遥感影像河流的精确提取[J]. 中国图象图形学报, 2013, 18(4):421-428.
[12] Shen Z F, Xia L G, Li J L, et al. Automatic and high-precision extraction of rivers from remotely sensed images with Gaussian normalized water index[J]. Journal of Image and Graphics, 2013, 18(4):421-428.
[13] 徐涵秋. 利用改进的归一化差异水体指数(MNDWI)提取水体信息的研究[J]. 遥感学报, 2005, 9(5):589-595.
[13] Xu H Q. A study on information extraction of water body with the modified normalized difference water index (MNDWI)[J]. Journal of Remote Sensing, 2005, 9(5):589-595.
[14] Rogers A S, Kearney M S. Reducing signature variability in unmixing coastal marsh thematic mapper scenes using spectral indices[J]. International Journal of Remote Sensing, 2004, 25(12):2317-2335.
doi: 10.1080/01431160310001618103 url: https://www.tandfonline.com/doi/full/10.1080/01431160310001618103
[15] McFEETERS S K. The use of the normalized difference water index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing, 1996, 17(7):1425-1432.
doi: 10.1080/01431169608948714 url: https://www.tandfonline.com/doi/full/10.1080/01431169608948714
[16] 段纪维, 钟九生, 江丽, 等. 基于GF-2影像的雨后洪涝区超绿水体指数提取方法[J]. 地理与地理信息科学, 2021, 37(3):35-41.
[16] Duan J W, Zhong J S, Jiang L, et al. Extraction method of ultra-green water index for flood area after rain based on GF-2 image[J]. Geography and Geo-Information Science, 2021, 37(3):35-41.
[17] 邹橙, 杨学志, 董张玉, 等. 基于GF-2遥感影像的一种快速水体信息提取方法[J]. 图学学报, 2019, 40(1):99-104.
[17] Zhou C, Yang X Z, Dong Z Y, et al. A fast water information extraction method based on GF-2 remote sensing image[J]. Journal of Graphics, 2019, 40(1):99-104.
[18] 谷金英, 晏明, 张晓娇, 等. 利用高分一号影像提取水体信息的方法研究[J]. 农业与技术, 2018, 38(11):24-26,109.
[18] Gu J Y, Yan M, Zhang X J, et al. Research on the method of extracting water information from gaofen-1 image[J]. Agriculture and Technology, 2018, 38(11):24-26,109.
[19] 陈文倩, 丁建丽, 李艳华, 等. 基于国产GF-1遥感影像的水体提取方法[J]. 资源科学, 2015, 37(6):1166-1172.
[19] Chen W Q, Ding J L, Li Y H, et al. Extraction of water information based on China-made GF-1 remote sense image[J]. Resources Science, 2015, 37(6):1166-1172.
[20] 王冬梅, 陈琳, 冯峰. 面向对象的GF-2影像水体信息提取研究[J]. 人民黄河, 2021, 43(5):80-83,90.
[20] Wand D M, Chen L, Feng F. Study on water information extraction from GF-2 image based on object-oriented method[J]. Yellow River, 2021, 43(5):80-83,90.
[21] 黄帅, 丁建丽, 李艳华. 面向对象的国产GF-1遥感影像水体信息提取研究[J]. 人民长江, 2016, 47(5):23-28.
[21] Huang S, Ding J L, Li Y H. Study of water information extraction based on domestic GF-1 remote sensing image by using object-oriented method[J]. Yangtze River, 2016, 47(5):23-28.
[22] 洪亮, 黄雅君, 杨昆, 等. 复杂环境下高分二号遥感影像的城市地表水体提取[J]. 遥感学报, 2019, 23(5):871-882.
[22] Hong L, Huang Y J, Yang K, et al. Study on urban surface water extraction from heterogeneous environments using GF-2 remotely sensed images[J]. Journal of Remote Sensing, 2019, 23(5): 871-882.
[23] 王胜蕾. 基于水色指数的大范围长时序湖库水质遥感监测研究[D]. 北京: 中国科学院大学(中国科学院遥感与数字地球研究所), 2018.
[23] Wang S L. Large-scale and long-time water quality remote sensing monitoring over lakes based on water color index[D]. Beijing: University of Chinese Academy of Sciences, 2018.
[24] 段秋亚, 孟令奎, 樊志伟, 等. GF-1卫星影像水体信息提取方法的适用性研究[J]. 国土资源遥感, 2015, 27(4):79-84.doi: 10.6046/gtzyyg.2015.04.13.
doi: 10.6046/gtzyyg.2015.04.13
[24] Duan Q Y, Meng L K, Fan Z W, et al. Applicability of the water information extraction method based on GF-1 image[J]. Remote Sensing for Land and Resources, 2015, 27(4):79-84.doi: 10.6046/gtzyyg.2015.04.13.
doi: 10.6046/gtzyyg.2015.04.13
[25] Jain S K, Singh R D, Jain M K, et al. Delineation of flood-prone areas using remote sensing techniques[J]. Water Resources Management, 2005, 19(4):333-347.
doi: 10.1007/s11269-005-3281-5 url: http://link.springer.com/10.1007/s11269-005-3281-5
[26] Zhang F, Li J, Zhang B, et al. A simple automated dynamic thresho-ld extraction method for the classification of large water bodies from Landsat8 OLI water index images[J]. International Journal of Remote Sensing, 2018, 39(11):3429-3451.
doi: 10.1080/01431161.2018.1444292 url: https://www.tandfonline.com/doi/full/10.1080/01431161.2018.1444292
[27] Fieuzal R, Sicre C M, Baup F. Estimation of corn yield using multi-temporal optical and Radar satellitedata and artificial neural networks[J]. International Journal of Applied Earth Observation and Geoinformation, 2017, 57(1):14-23.
doi: 10.1016/j.jag.2016.12.011 url: https://linkinghub.elsevier.com/retrieve/pii/S0303243416302094
[28] 刘双童, 王明孝, 杨树文, 等. 基于GF-2高分辨率遥感影像的水体提取方法研究[J]. 全球定位系统, 2018, 43(6):37-43.
[28] Liu S T, Wang M X, Yang S W, et al. Research on water body extraction method based on GF-2 high resolution remote sensing image[J]. GNSS World of China, 2018, 43(6):37-43.
[1] WU Weichao, YE Fawang. Cloud detection of Sentinel-2 images for multiple backgrounds[J]. Remote Sensing for Natural Resources, 2023, 35(3): 124-133.
[2] XI Lei, SHU Qingtai, SUN Yang, HUANG Jinjun, SONG Hanyue. Optimizing an ICESat2-based remote sensing estimation model for the leaf area index of mountain forests in southwestern China[J]. Remote Sensing for Natural Resources, 2023, 35(3): 160-169.
[3] PARIHA Helili, ZAN Mei. Spatio-temporal changes and influencing factors of ecological environments in oasis cities of arid regions[J]. Remote Sensing for Natural Resources, 2023, 35(3): 201-211.
[4] LIANG Jintao, CHEN Chao, ZHANG Zili, LIU Zhisong. A random forest-based method integrating indices and principal components for classifying remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(3): 35-42.
[5] LI Zhixin, WANG Mengfei, JIA Weijie, JI Song, WANG Yufei. A method for identifying the number of building floors based on shadow information[J]. Remote Sensing for Natural Resources, 2023, 35(3): 97-106.
[6] WU Yuxin, WANG Juanle, HAN Baomin, YAN Xinrong. Forest classification for Motuo County: A method based on spatio-temporal-spectral characteristics[J]. Remote Sensing for Natural Resources, 2023, 35(1): 180-188.
[7] ZHANG Hao, GAO Xiaohong, SHI Feifei, LI Runxiang. Sentinel-2 MSI and Sentinel-1 SAR based information extraction of abandoned land in the western Loess Plateau:A case study of Minhe County in Qinghai[J]. Remote Sensing for Natural Resources, 2022, 34(4): 144-154.
[8] DENG Jingwen, TIAN Yichao, ZHANG Qiang, TAO Jin, ZHANG Yali, HUANG Shengguang. Application of airborne LiDAR in the estimation of the mean height of mangrove stand[J]. Remote Sensing for Natural Resources, 2022, 34(3): 129-137.
[9] WANG Xuejie, SHI Guoping, ZHOU Ziqin, ZHEN Yang. Revision of solar radiation product ERA5 based on random forest algorithm[J]. Remote Sensing for Natural Resources, 2022, 34(2): 105-111.
[10] ZHU Qi, GUO Huadong, ZHANG Lu, LIANG Dong, LIU Xuting, WAN Xiangxing. Classification of tropical natural forests in Hainan Island based on multi-temporal Landsat8 remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(2): 215-223.
[11] ERPAN Anwar, MAMAT Sawut, MAIHEMUTI Balati. Recognition of cotton distribution based on GF-2 images and Unet model[J]. Remote Sensing for Natural Resources, 2022, 34(2): 242-250.
[12] SUN Xiao, PENG Junhuan, ZHAO Feng, WANG Xiaoyang, LYU Jie, ZHANG Dengfeng. Principal component selection method for hyperspectral remote sensing images based on spatial statistics[J]. Remote Sensing for Natural Resources, 2022, 34(2): 37-46.
[13] WU Linlin, LI Xiaoyan, MAO Dehua, WANG Zongming. Urban land use classification based on remote sensing and multi-source geographic data[J]. Remote Sensing for Natural Resources, 2022, 34(1): 127-134.
[14] LIU Mingxing, LIU Jianhong, MA Minfei, JIANG Ya, ZENG Jingchao. Monitoring of Zanthoxylum bungeanum Maxim planting using GF-2 PMS images and the random forest algorithm: A case study of Linxia, Gansu Province[J]. Remote Sensing for Natural Resources, 2022, 34(1): 218-229.
[15] GUO Xiaozheng, YAO Yunjun, JIA Kun, ZHANG Xiaotong, ZHAO Xiang. Information extraction of Mars dunes based on U-Net[J]. Remote Sensing for Natural Resources, 2021, 33(4): 130-135.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech