Water Body Area Extraction from SAR Image based on Improved SVM Classification Method

被引：0
|
作者：
Qiu F. [1 ,2 ,3 ,5 ]
Guo Z. [1 ,3 ]
Zhang Z. [1 ,3 ]
Wei X. [1 ,3 ]
Jing M. [4 ]
机构：
[1] Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing
[2] University of Chinese Academy of Sciences, School of Electronic, Electrical and Communication Engineering, Beijing
[3] China-Sri Lanka Joint Center for Water Technology Research and Demonstration by the Chinese Academy of Sciences, Beijing
[4] The Pennsylvania State University, Engineering College, 16802, PA
[5] China Siwei Surveying and Mapping Technology Company Limited, Beijing
来源：
Journal of Geo-Information Science | 2022年 / 24卷 / 05期
关键词：
Complex water environment; SDWI; Sentinel-1 SAR data; Sri Lanka Mahaweli River Basin; SVM; Terrain features; Texture features; Water extraction;
D O I：
10.12082/dqxxkx.2022.210095
中图分类号：
学科分类号：
摘要：
In cloudy and rainy regions with complex surface environments, water body extraction based on Synthesis Aperture Radar (SAR) image is easily interfered by other surface features such as paddy field and mountain shadow. The traditional gray threshold method and SVM method fail to take into account the differences in texture and terrain information between water and other surface features, resulting in the low accuracy of water body extraction. In this paper, we first use refined Lee filter to pre-process the SAR image, then extract terrain features by modeling DEM and calculating the slope information. We extract the texture features, including the homogeneity (hom), Angular Second Moment (ASM), and entropy (ENT), by calculating image Gray Level Co-occurrence Matrix (GLCM) based on the SAR image. Meanwhile, polarization band information of the SAR image and SDWI index are combined to form the SVM feature space for water body extraction. Finally, an improved SVM classification method for water body extraction is proposed by fusing terrain features with image texture features. Compared with SDWI water index method and traditional SVM method based on Sentinel-1 SAR data, it is found that the improved SVM method can remove the shadows of paddy field and mountain. The result of water surface extraction by the improved SVM method is more complete than that of traditional SVM method. The result also shows that the improved SVM method performs better than SDWI method and traditional SVM method in terms of overall accuracy, kappa coefficient, leakage rate, and error rate. The overall accuracy of the improved SVM method is 98.06%, which is 23.24% and 5.49% higher than that of SDWI method and traditional SVM method, respectively, demonstrating that the improved SVM method can effectively improve the extraction accuracy of surface water in complex environments. The developed method is applied to monthly water extraction and change analysis of Mahaweli River Basin in 2018, which proves that the method can effectively solve the problems of mountain shadow and paddy field misclassification. The improved SVM method can realize the accurate and complete large-scale water body information extraction in complex surface environments. © 2022, Science Press. All right reserved.
引用
收藏
页码：940 / 948
页数：8
相关论文
共 19 条
  • [1] Li D, Wu B S, Chen B W, Et al., Review of water body information extraction based on satellite remote sensing, Journal of Tsinghua University (Science and Technology), 60, 2, pp. 147-161, (2020)
  • [2] Zhou P, Xie Y L, Jiang G X, Et al., Advances on water body information extraction from remote sensing imagery, Remote Sensing Information, 35, 5, pp. 9-18, (2020)
  • [3] Zeng L F, Li L, Wan L H., SAR-based fast flood mapping using sentinel-1 imagery, Geomatics World, 22, 5, pp. 100-103, (2015)
  • [4] Otsu N., A threshold selection method from gray-level histograms, IEEE Transactions on Systems, Man, and Cybernetics, 9, 1, pp. 62-66, (1979)
  • [5] Kiani H, Safabakhsh R, Khadangi E., Fast recursive segmentation algorithm based on Kapur's entropy[C], 2009 2nd International Conference on Computer, Control and Communication, pp. 1-6, (2009)
  • [6] Cui Q, Mao X D, Chen D Q, Et al., Research on automation and operationality in water extraction based on GF-3, China Agricultural Informatics, 31, 5, pp. 57-65, (2019)
  • [7] Li J G, Huang S F, Li J R., Research on extraction of water body from ENVISAT ASAR images: A modified Otsu threshold method, Journal of Natural Disasters, 19, 3, pp. 139-145, (2010)
  • [8] Chen Y Y, Zheng J Z, Wei H H, Et al., Water information extraction of Nanjing city based on sentinel-1A data, Geospatial Information, 18, 9, pp. 62-65, (2020)
  • [9] Zhan N Y, Li X T, Lu J X, Et al., Water body information extraction by Sentinel-1 radar data based on SLIC, Yangtze River, 51, 4, pp. 213-217, (2020)
  • [10] Jia S C, Xue D J, Li C R, Et al., Study on new method for water area information extraction based on Sentinel-1 data, Yangtze River, 50, 2, pp. 213-217, (2019)
12