基于改进SVM算法的Sentinel-2A MSI遥感影像水体提取

doi:10.13474/j.cnki.11-2246.2025.0210

摘要/Abstract

摘要： 地表水体信息的准确提取对于水资源研究具有重要意义,本文以Sentinel-2影像为研究数据,贵州省贵阳市红枫湖为研究区域,提出了结合主成分分析(PCA)、随机森林(RF)和支持向量机(SVM)的改进SVM水体提取算法。首先,对原始波段进行PCA降维,并利用移动窗口对所得成分进行灰度共生矩阵(GLCM)纹理和小波纹理计算;然后,结合原始光谱数据基于RF进行特征优选;最后,选择纹理最佳窗口大小并基于SVM算法对湖泊水体进行提取。结果表明,本文方法的水体提取总体精度高于其他方法,其总体精度和Kappa系数分别达98.87%和98.49%,水体信息更加完整。

关键词: 水体提取, 支持向量机, 随机森林, 纹理特征, 移动窗口

Abstract: The accurate extraction of surface water information is of great significance for water resources research. In this paper, using the Sentinel-2 image for research data, we propose the improvement of the SVM water extraction algorithm by principal component analysis (PCA), random forest (RF) and support vector machine(SVM).Firstly, the dimension of the original band is reduced by PCA and the composition of gray level co-occurrence matrix (GLCM) texture and wavelet texture are calculated by using the moving window. Then, the original spectral data is used for feature optimization based on RF. Finally, the optimal texture calculation window is selected and the lake water is extracted based on the SVM algorithm. Results on the surface, the overall accuracy of this method is higher than that of other methods, and the overall accuracy and Kappa coefficient are 98.87% and 98.49% respectively, and the water information is more complete.

Key words: water extraction, support vector machine, random forest, texture features, mobile window

中图分类号:

P237

李升海, 张俊, 唐海林. 基于改进SVM算法的Sentinel-2A MSI遥感影像水体提取[J]. 测绘通报, 2025, 0(2): 53-57,76.

LI Shenghai, ZHANG Jun, TANG Hailin. Sentinel-2A MSI remote sensing image water extraction based on improved SVM algorithm[J]. Bulletin of Surveying and Mapping, 2025, 0(2): 53-57,76.

参考文献

[1] 赵辉.基于Landsat数据的鄱阳湖面积动态监测及其与水位关系研究[D].北京:中国地质大学(北京),2016.
[2] 张琪曼,杨景飞.西藏自治区那曲地区湖泊提取及面积动态变化[J].测绘通报,2023(S1):92-97.
[3] 吴渊,陈剑,陈鹏.基于Res-Unet的色林错湖20年水体面积变化提取研究[J].环境生态学,2022,4(11):6-12.
[4] 王琳,谢洪波,文广超,等.基于Landsat8的含蓝藻湖泊水体信息提取方法研究[J].国土资源遥感,2020,32(4):130-136.
[5] 张洁,王心源,高超,等.基于Landsat TM数据的东平湖水体提取方法研究[J].测绘与空间地理信息,2012,35(4):23-27.
[6] 刘桂林,张落成,刘剑,等.基于Landsat TM影像的水体信息提取[J].中国科学院大学学报,2013,30(5):644-650.
[7] 杨树文,薛重生,刘涛,等.一种利用TM影像自动提取细小水体的方法[J].测绘学报,2010,39(6):611-617.
[8] 王春霞,张俊,李屹旭,等.一种基于Landsat 8的多波段组合水体指数模型[J].测绘通报,2022(5):20-25.
[9] 王仁军,刘宝康,杜玉娥,等.基于GF-6的可可西里典型湖泊水体面积提取方法研究[J].测绘通报,2022(5):32-37.
[10] 马海超,王崇倡,何昭宁,等.面向GF-7影像的绿波改正归一化水体指数构建[J].测绘通报,2023(5):38-43.
[11] 康辉,窦文章,韩灵怡,等.基于DeepLabv3+模型的地表水体快速遥感监测[J/OL].自然资源遥感,2023(2023-11-27).https://kns.cnki.net/kcms/detail/10.1759.p.20231124.1256.002.html.
[12] YU Yongtao,HUANG Long,LU Weibin,et al.WaterHRNet:a multibranch hierarchical attentive network for water body extraction with remote sensing images[J].International Journal of Applied Earth Observation and Geoinformation,2022,115:103103.
[13] HIBJUR RAHAMAN M,ROSHANI,MASROOR M,et al.Integrating remote sensing derived indices and machine learning algorithms for precise extraction of small surface water bodies in the lower Thoubal river watershed,India[J].Journal of Cleaner Production,2023,422:138563.
[14] 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.
[15] 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.
[16] 骆剑承,周成虎,梁怡,等.支撑向量机及其遥感影像空间特征提取和分类的应用研究[J].遥感学报,2002,6(1):50-55.
[17] 张德军,杨世琦,王永前,等.基于GF-1数据的三峡库区水体信息精细化提取[J].人民长江,2019,50(9):233-239.
[18] 周婷,汪炎,邹俊,等.基于PCA和SVM的遥感影像水体提取方法及验证[J].水资源保护,2023,39(2):180-189.
[19] 马肖肖,程博,刘岳明,等.基于极化特征和纹理特征的PolSAR影像建筑物提取方法[J].中国科学院大学学报,2019,36(5):682-693.
[20] HARALICK R M,SHANMUGAM K,DINSTEIN I.Textural features for image classification[J].IEEE Transactions on Systems,Man,and Cybernetics,1973,SMC-3(6):610-621.
[21] SINGH A,ARMSTRONG R T,REGENAUER-LIEB K,et al.Rock characterization using gray-level co-occurrence matrix:an objective perspective of digital rock statistics[J].Water Resources Research,2019,55(3):1912-1927.
[22] 黄昕,张良培,李翠琳.基于小波变换的影像纹理特征提取试验[J].测绘信息与工程,2005,30(6):7-9.
[23] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[24] 黄梅,朱焱.基于随机森林特征重要性的K-匿名特征优选[J].计算机应用与软件,2020,37(3):266-270.
[25] ZHANG Fangfang,ZHANG Bing,LI Junsheng,et al.Comparative analysis of automatic water identification method based on multispectral remote sensing[J].Procedia Environmental Sciences,2011,11:1482-1487.
[26] 叶磊,韦克苏,李德仑,等.基于改进RF特征选择策略的烤烟油分高光谱特征分析[J].中国农机化学报,2021,42(8):196-202.