Please wait a minute...
img

官方微信

遥感技术与应用  2020, Vol. 35 Issue (2): 448-457    DOI: 10.11873/j.issn.1004-0323.2020.2.0448
遥感应用     
基于GF-1和Sentinel-1A的漓江流域典型地物信息提取
唐廷元(),付波霖(),何素云,娄佩卿,闭璐
桂林理工大学 测绘地理信息学院, 广西 桂林 541000
Identification of Typical Land Features in the Lijiang River Basin with Fusion Optics and Radar
Tingyuan Tang(),Bolin Fu(),Suyun He,Peiqing Lou,Lu Bi
Guilin University of Technology, Guilin 541000, China
 全文: PDF(6317 KB)   HTML
摘要:

漓江流域是桂林山水的核心,保护漓江流域生态环境已成为国家战略。以漓江流域为研究区域,以GF-1多光谱影像和SAR影像为数据源,采用小波融合算法将GF-1多光谱影像和SAR VV极化的后向散射影像进行影像融合,再利用随机森林算法分别对GF-1多光谱影像、GF-1和Sentinel融合影像构建典型地物高精度识别模型,提取与漓江流域生态环境紧密相关的河流、针叶林、阔叶林、水田、旱地以及居民地等地物类型。研究结果表明:①在95%置信区间内,基于GF-1影像分类的总体分类精度达到96.15%,基于GF-1和Sentinel-1A后向散射系数的影像总体分类精度达到了94.40%;②河流、阔叶林和旱地在基于GF-1多光谱影像的分类精度中分别达到了97.74%、93.20%、90.90%,比基于融合GF-1多光谱和SAR的数据分别高出7.57%、8.96%和1.22%,其余地物类型两者分类精度相近;③GF-1多光谱和SAR数据的融合中,利用了小波变换进行图像融合,发现融合图像的喀斯特地貌突出,增加了地物特征的差异性。

关键词: 漓江流域光学遥感合成孔径雷达随机森林算法地物遥感识别    
Abstract:

Lijiang River is the core of Guilin's landscape. Protecting the ecological environment of Lijiang River Basin has become a national strategy. In this paper, Lijiang River Basin was used as the research area. The GF-1 multispectral image and SAR image were used as the data source. The wavelet fusion algorithm was used to fuse the GF-1 multispectral image and the SAR VV polarized backscatter image. Using random forest algorithm to construct a high-precision recognition model for GF-1 multispectral imagery, GF-1 and sentinel fusion images. The model can extract rivers, coniferous forests, broad-leaved forests, paddy fields, drylands, residential land and other land types that are closely related to the ecological environment of the Lijiang River. The results show that ①the overall accuracy based on GF-1 image classification reaches 96.15% in the 95% confidence interval, and the overall accuracy based on GF-1 and sentinel-1A backscatter coefficient reaches 94.40%. ②The classification accuracy of rivers, broad-leaved forests and drylands based on GF-1 multispectral images reached 97.74%, 93.20%, and 90.90%. They are 7.57%, 8.96%, and 1.22% higher than those based on the fused GF-1 multispectral and SAR data, respectively. The classification accuracy of the other features is similar. ③In the fusion of GF-1 multispectral and SAR data, wavelet transform was used for image fusion. It was found that the karst topography of the fusion image was prominent, which increased the difference of the features of the ground features.

Key words: Lijiang River    Optical remote sensing    Synthetic Aperture Radar    Random Forest    Object identification
收稿日期: 2018-12-28 出版日期: 2020-07-10
ZTFLH:  P23  
基金资助: 国家自然科学青年基金项目“基于主被动遥感的沼泽植被群丛时空分布与水文情势耦合研究”(41801071);广西自然科学青年基金项目“基于主被动遥感的北部湾红树林群丛时空分布与水文情势耦合研究”(2018GXNSFBA281015);桂林理工大学科研启动基金项目(GUTQDJJ2017096┫共同资助)
通讯作者: 付波霖     E-mail: TangtyRS@126.com;fbl2012@126.com
作者简介: 唐廷元(1995-),男,重庆人,硕士研究生,主要从事遥感图像智能处理研究。E?mail: TangtyRS@126.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
唐廷元
付波霖
何素云
娄佩卿
闭璐

引用本文:

唐廷元,付波霖,何素云,娄佩卿,闭璐. 基于GF-1和Sentinel-1A的漓江流域典型地物信息提取[J]. 遥感技术与应用, 2020, 35(2): 448-457.

Tingyuan Tang,Bolin Fu,Suyun He,Peiqing Lou,Lu Bi. Identification of Typical Land Features in the Lijiang River Basin with Fusion Optics and Radar. Remote Sensing Technology and Application, 2020, 35(2): 448-457.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2020.2.0448        http://www.rsta.ac.cn/CN/Y2020/V35/I2/448

图1  研究区位置及漓江流域概况
图2  SAR影像预处理
图3  GF-1和SAR融合图像中的喀斯特地貌
图4  技术方案
数据集mtryntree
GF-1171 500
GF-1&Sentinel-1A231 500
表1  Random Forest 算法中mtry 和ntree参数
图5  基于GF-1多光谱图像的分类专题图
精度指标评估/%标准差/%95%置信区间/%
总体分类精度96.150.0496.0796.23
Kappa系数91.950.0891.7992.11
表2  总体精度评价表
用户精度/%生产者精度/%
地物类型评估标准差95%区间评估标准差95%区间
河流99.230.0299.1999.2697.740.3297.1298.36
针叶林97.450.0397.3997.5297.310.0597.2297.40
阔叶林92.420.0592.3292.5293.200.0893.0593.36
水田93.980.0593.8994.0781.170.3580.4781.86
旱地95.300.0495.2195.3890.900.2290.4791.34
居民地97.220.0397.1697.2998.930.0598.8299.04
表3  漓江流域各类地物分类精度
参考地物类型
地物类型河流针叶林阔叶林水田旱地居民地总和
河流3 2060025003 231
针叶林2167 6014 372040171 979
阔叶林244 63360 346211384465 296
水田240291 030491 096
旱地00001 499741 573
居民地2400310411 73612 071
总和3 280172 23464 7471 2691 64911 863255 303
表4  混淆矩阵表
精度指标评估/%标准差/%95%置信区间/%
总体分类精度94.400.0594.3094.50
Kappa系数88.050.1187.8488.27
表5  总体精度评价表
用户精度/%生产者精度/%
地物类型评估标准差95%区间评估标准差95%区间
河流99.490.0299.4699.5390.170.6888.8391.51
针叶林94.300.0594.2094.4098.370.0498.2998.45
阔叶林94.430.0594.3394.5384.240.1184.0284.47
水田98.570.0398.5298.6281.350.6979.9982.72
旱地91.710.0691.5991.8389.680.3389.0490.32
居民地94.300.0594.2094.4099.540.0499.4699.61
表6  漓江流域各类地物分类精度
参考地物类型
地物类型河流针叶林阔叶林水田旱地居民地总和
河流2 5600011002 573
针叶林7136 0758 210070144 299
阔叶林1122 26043 895173311046 483
水田1200829008 41
旱地01001 217351 327
居民地1480061029 66310 247
总和2 839138 33652 1051 0191 3579 708205 818
表7  混淆矩阵表
影像集95%置信区间总体分类精度/%Kappa 系数
GF-196.150.92
GF-1&Sentinel-1A94.400.88
表8  总体分类精度比较表
图6  融合GF-1和Sentinel-1A图像的分类专题
图7  漓江流域各典型地物生产者精度对比分析
1 Luo B,Yang C,Chanussot J, et al. Crop Yield Estimation based on Unsupervised Linear Unmixing of Multidate Hyperspectral Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(1):162-173. doi:10.1109/TGRS.2012.2198826.
doi: 10.1109/TGRS.2012.2198826
2 Liu Huanjun, Yang Haoxuan, Xu Mengyuan, et al. Soil Classification based on Maximum Likelihood Method and Features of Multi-temporal Remote Sensing Images in Bare Soil Period[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018,34(14):132-139.
2 刘焕军,杨昊轩,徐梦园, 等.基于裸土期多时相遥感影像特征及最大似然法的土壤分类[J].农业工程学报,2018,34(14):132-139.
3 Fan Xuan, An Shaoshan, Xue Zhijinget al. Analysis on Spatial Variablity of Soil Organic Carbon and Nitrogen based on REML and MOM in a Small Watershed on Loess Plateau[J] Bulletin of Soil and Water Conservation, 2014,34(4):141-146.
3 方炫,安韶山,薛志婧, 等.基于最大似然法与矩法的黄土高原小流域土壤碳氮空间变异分析[J].水土保持通报,2014,34(4):141-146.
4 Zhang Jing, Liu Zhongbao, Song Wenai, et al. Stellar Spectra Classification Method based on Multi-Class Support Vector Machine[J]. Spectroscopy and Spectral Analysis, 2018,38(7):2307-2310.
4 张静,刘忠宝,宋文爱, 等.基于多类支持向量机的恒星光谱分类方法[J].光谱学与光谱分析,2018,38(7):2307-2310.
5 Liu Yi, Du Peijun, Zheng Hui, et al. Classification of China Small Satellite Remote Sensing Image based on Random Forests[J]. Science of Surveying and Mapping, 2012,37(4):194-196.
5 刘毅,杜培军,郑辉, 等.基于随机森林的国产小卫星遥感影像分类研究[J].测绘科学,2012,37(4):194-196.
6 Zhang Xiaoyu, Li Fengri, Zhen Zhen, et al. Forest Vegetation Classification of Landsat 8 Remote Sensing Image based on Random Forests Model[J]. Journal of Northeast Forestry University,2016,44(6):53-57, 74.
6 张晓羽,李凤日,甄贞, 等.基于随机森林模型的陆地卫星-8遥感影像森林植被分类[J].东北林业大学学报,2016,44(6):53-57, 74.
7 Fan Chi, Jiang Hong. Precise Extraction of Buildings' Information in WorldView2 Images based on Random Forests[J]. Geospatial Information, 2016,14(1):58-62, 5.
7 范驰,江洪.基于随机森林的WorldVew2i影像建筑物精细提取[J].地理空间信息,2016,14(1):58-62, 5.
8 Deng Liuyang, Shen Zhanfeng, Ke Yingming, et al. Winter Wheat Planting Area Extraction Using Multi-temporal Remote Sensing Images based on Field Parcel[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(21): 157-164.
8 邓刘洋,沈占锋,柯映明, 等.基于地块尺度多时相遥感影像的冬小麦种植面积提取[J].农业工程学报,2018,34(21):157-164.
9 Bao W X, Zhu X L. A Novel Remote Sensing Image Fusion Approach Research based on HSV Space and Bi-orthogonal Wavelet Packet Transform[J]. Journal of the Indian Society of Remote Sensing,2015,43(3).doi:10.1007/s12524-014-0430-4.
doi: 10.1007/s12524-014-0430-4
10 Miao Q G,Xu P F,Shi C. A Novel Algorithm of Remote Sensing Image Fusion based on Shearlets and PCNN[J].Neurocomputing,2013,117:47-53. doi:10.1016/j.neucom. 2012. 10.025.
doi: 10.1016/j.neucom. 2012. 10.025
11 Yang W, Wang J, Guo J. A Novel Algorithm for Satellite Images Fusion based on Compressed Sensing and PCA[J]. Mathematical Problems in Engineering, 2013(pt.11):708985,1-708985.10. doi:10.1155/2013/708985.
doi: 10.1155/2013/708985
12 Liu Na, Tian Dawei. Research on Image Fusion Algorithm based on Wavelet Transform[J]. Modern Electronics Technique,2018,41(7):71-74, 79.
12 刘娜,田大为.基于小波变换的图像融合算法研究[J].现代电子技术,2018,41(7):71-74, 79.
13 Guo Zhiqiang. Wavelet Transform Image Fusion based on Regional Features[J]. Journal of Wuhan University of Technology,2005,27(2):65-67, 71.
13 郭志强.基于区域特征的小波变换图像融合方法[J].武汉理工大学学报,2005,27(2):65-67, 71.
14 Wang Linyan. A Consideration of Country's Integrated Informing Experimental Area Construction of Guilin City from the View of Culture[J]. Ecological Economy,2013(1):123-126.
14 王林燕.从文化的视角思考桂林国家旅游综合改革试验区建设[J].生态经济,2013(1):123-126.
15 Chang Lihong,Feng Xiangchu,Zhang Rui.Image Fusion Scheme based on Quaternion Wavelet Transform and Sparse Representation[J]. Systems Engineering and Electronics,2017,39(7):1633-1639.
15 常莉红,冯象初,张瑞.四元数小波变换联合稀疏表示的图像融合[J].系统工程与电子技术,2017,39(7):1633-1639.
16 Wu Xiaoyan, Chai Jing, Liu Fan, et al. Remote Sensing Image Fusion based on Minimum Hausdorff Distance and Non-sampled Shearlet Transform[J]. Acta Photonica Sinica,2018,47(2):181-192.
16 武晓焱,柴晶,刘帆, 等.基于最小Hausdorff距离和NSST的遥感图像融合[J].光子学报,2018,47(2):181-192.
17 Li Xu, Gao Yanan, Shigang Yue. A Novel Scale-aware Pansharpening Method[J]. Journal of Astronautics,2017,38(12):1348-1353.
17 李旭, 高雅楠, Shigang Yue.一种尺度感知型遥感图像融合新方法[J]. 宇航学报, 2017, 38(12): 1348-1353.
18 Mo Caijian, Tian Jianrong, Wu Fengqianget al. Remote Sensing Images Fusion Algorithm based on Weighted Wavelet Analysis[J]. Journal of Jilin University(Science Edition),2018,56(3):617-624.
18 莫才健,田健榕,武锋强,等.基于加权小波分析的遥感图像融合算法[J].吉林大学学报(理学版),2018,56(3):617-624.
19 Yuan Guixia, Zhou Xianchun. Remote Sensing Image Fusion Algorithm based on Biorthogonal Wavelet Transform Coupled with Regional Gradient Features[J]. Optical Technique,2018,44(6):690-697.
19 袁桂霞,周先春.基于双正交小波变换耦合区域梯度特征的遥感图像融合算法[J].光学技术,2018,44(6):690-697.
20 Wan Jianhua, Zang Jinxia, Liu Shanwei. Fusion and Classification of SAR and Optical Image with Consideration of Polarization Characteristics[J]. Acta Optica Sinica,2017,37(6):284-293.
20 万剑华,臧金霞,刘善伟.顾及极化特征的SAR与光学影像融合与分类[J].光学学报,2017,37(6):284-293.
21 Lei Wu, Liao Wenjian, Peng Yanbing. Search Rank Model based on Random Forests and LambdaMART[J]. Computer and Modernization,2017(3):54-58.
21 雷武,廖闻剑,彭艳兵.基于随机森林与LambdaMART的搜索排序模型[J].计算机与现代化,2017(3):54-58.
22 Liu Jiafu, Li Linfeng, Ren Chunyinget al. Information Extraction of Coastal Wetlands in Yellow River Estuary by Optimal Feature-based Random Forest Model[J] Wetland Science,2018,16(2):97-105.
22 刘家福,李林峰,任春颖, 等.基于特征优选的随机森林模型的黄河口滨海湿地信息提取研究[J].湿地科学,2018,16(2):97-105.
23 Liu Shu, Jiang Qigang, Ma Yueet al. Object-oriented Wetland Classification based on Hybrid Feature Selection Method Combining with Relief F,Multi-objective Genetic Algorithm and Random Forest[J]. Transactions of the Chinese Society for Agricultural Machinery,2017,48(1):119-127.
23 刘舒,姜琦刚,马玥, 等.基于多目标遗传随机森林特征选择的面向对象湿地分类[J].农业机械学报,2017,48(1):119-127.
24 Zhan Guoqi, Yang Guodong, Wang Fengyanet al. The Random Forest Classification of Wetland from GF-2 Imagery based on the Optimized Feature Space[J] Journal of Geo-Information Science,2018,20(10):1520-1528.
24 詹国旗,杨国东,王凤艳, 等.基于特征空间优化的随机森林算法在GF-2影像湿地分类中的研究[J].地球信息科学学报,2018,20(10):1520-1528.
25 Ma Yue, Jiang Qigang, Meng Zhiguoet al. Classification of Land Use in Farming Area based on Random Forest Algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery,2016,47(1):297-303.
25 马玥,姜琦刚,孟治国, 等.基于随机森林算法的农耕区土地利用分类研究[J].农业机械学报,2016,47(1):297-303.
26 Zhang Yingying, Cai Xiaobin, Song Xinxinet al. Remote Sensing Information Extraction of Hydrophyte in Honghu Lake based on Decision Tree[J]. Wetland Science,2018,16(2):213-222.
26 张莹莹,蔡晓斌,宋辛辛, 等.基于决策树的洪湖水生植物遥感信息提取[J].湿地科学,2018,16(2):213-222.
27 He Yuanhuizi, Wang Changlin, Jia Huicong,et al. Research on Extraction of Winter Wheat based on Random Forest[J]. Remote Sensing Technology and Application, 2018,33(6):1132-1140.
27 贺原惠子,王长林,贾慧聪, 等.基于随机森林算法的冬小麦提取研究[J].遥感技术与应用,2018,33(6):1132-1140.
28 Liu Biao, Lu Zhe, Huang Yu-wei,et al. Comparative Study on Neural Network Structures in Power Analysis[J]. Journal of Shandong University(Natural Science Editon),2019,54(1):60-66,78.
28 刘飚,路哲,黄雨薇, 等.神经网络结构在功耗分析中的性能对比[J].山东大学学报(理学版),2019,54(1):60-66,78.
29 Mo Lijiang, Cao Yu, Hu Yuanman, et al. Object-oriented Classification for Satellite Remote Sensing of Wetlands: A Case Study in Southern Hangzhou Bay Area[J]. Wetland Science,2012,10(2):206-213.
29 莫利江,曹宇,胡远满, 等.面向对象的湿地景观遥感分类——以杭州湾南岸地区为例[J].湿地科学,2012,10(2):206-213.
30 Zhang Ci, Zang Shuying, Jin Zhu, et al. Remote Sensing Classification for Zhalong Wetlands based on Support Vector Machine[J]. Wetland Science,2011,9(3):263-269.
30 张策,臧淑英,金竺, 等.基于支持向量机的扎龙湿地遥感分类研究[J].湿地科学,2011,9(3):263-269.
[1] 廖凯涛,齐述华,王成,王点. 结合GLAS和TM卫星数据的江西省森林高度和生物量制图[J]. 遥感技术与应用, 2018, 33(4): 713-720.
[2] 万玲,尤红建,程跃兵,卢晓军. 合成孔径雷达图像分割研究进展[J]. 遥感技术与应用, 2018, 33(1): 10-24.
[3] 熊伟,徐永力,姚力波,崔亚奇. 基于SVM的高分辨率SAR图像舰船目标检测算法[J]. 遥感技术与应用, 2018, 33(1): 119-127.
[4] 谢亚楠,周明亮,刘志坤. 合成孔径雷达反演降雨量算法的研究进展[J]. 遥感技术与应用, 2017, 32(4): 624-633.
[5] 李海英,温卫斌,王芳,付强,肖媛. 表层穿透雷达在月球与深空探测应用中的研究进展及趋势[J]. 遥感技术与应用, 2017, 32(4): 634-642.
[6] 姜萍,刘修国,陈启浩,邵芳芳. 利用多尺度SVM-CRF模型的极化SAR图像建筑物提取[J]. 遥感技术与应用, 2017, 32(3): 475-482.
[7] 张祥,陈报章,赵慧,汪磊. 基于时序Sentinel-1A数据的农田土壤水分变化检测分析[J]. 遥感技术与应用, 2017, 32(2): 338-345.
[8] 袁春琦,徐佳,程圆娥,陈媛媛,许康. 基于协同训练与集成学习的极化SAR图像半监督分类[J]. 遥感技术与应用, 2017, 32(2): 380-385.
[9] 孙景,唐丹玲,潘刚. Radarsat2全极化数据在监测南海溢油事件中的方法研究[J]. 遥感技术与应用, 2016, 31(6): 1181-1189.
[10] 李兰,陈尔学,李增元,冯琦,赵磊. 合成孔径雷达森林树高和地上生物量估测研究进展[J]. 遥感技术与应用, 2016, 31(4): 625-633.
[11] 王俊,秦其明,叶昕,王建华,秦雪彬,杨绣丞. 高分辨率光学遥感图像建筑物提取研究进展[J]. 遥感技术与应用, 2016, 31(4): 653-662.
[12] 李婷,程博,尤淑撑. 基于半监督鉴别分析的高分辨率SAR影像建筑区提取[J]. 遥感技术与应用, 2016, 31(2): 239-246.
[13] 孙建勇,车 涛,段克勤,戴礼云. 冰沟流域积雪面积比例与雪水当量关系初探[J]. 遥感技术与应用, 2015, 30(6): 1085-1094.
[14] 蒋少峰,王超,吴樊,张波,汤益先,张红. 基于结构特征分析的COSMO-SkyMed图像商用船舶分类算法[J]. 遥感技术与应用, 2014, 29(4): 607-615.
[15] 李文梅,李增元,陈尔学,孙晗伟,王馨爽. 极化相干层析反演森林垂直结构原理与方法研究[J]. 遥感技术与应用, 2014, 29(2): 232-239.