Please wait a minute...
 
Remote Sensing for Natural Resources    2021, Vol. 33 Issue (4) : 105-110     DOI: 10.6046/zrzyyg.2020353
|
Information extraction methods of coastal wetland based on GF-3 fully polarimetric SAR data
HE Chenlinqiu1,2(), CHENG Bo1(), CHEN Jinfen1,2, ZHANG Xiaoping1,2
1. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
Download: PDF(2837 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

The study on the information extraction methods of coastal wetlands is highly significant for accurately grasping the distribution status of coastal wetlands and for protecting and managing the rare resources in coastal wetlands. To improve the information extraction precision of surface features in coastal wetland conservation areas, this paper screens the polarimetric decomposition features using the separability index and classifies fully polarimetric SAR images using the random forest method. The details are as follows. Based on the domestic GF-3 fully polarimetric radar images of the Liaohe River Estuary National Nature Reserve in Liaoning Province, five polarimetric target decomposition methods were used to extract polarimetric features, the separable index was adopted to optimize feature selection, and finally the random forest method was utilized to conduct the classification and accuracy assessment of surface features in the study area. The experiment results show that the classification accuracy of surface features in wetlands based on optimized polarimetric features was up to 75.47%. Meanwhile, the optimized polarimetric feature parameters can effectively avoid information redundancy and improve the information extraction accuracy of surface features in coastal wetland conservation areas.
Keywords coastal wetland      GF-3      selection of polarimetric features     
ZTFLH:  TP751  
Corresponding Authors: CHENG Bo     E-mail: heclq@radi.ac.cn;chengbo@radi.ac.cn
Issue Date: 23 December 2021
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Chenlinqiu HE
Bo CHENG
Jinfen CHEN
Xiaoping ZHANG
Cite this article:   
Chenlinqiu HE,Bo CHENG,Jinfen CHEN, et al. Information extraction methods of coastal wetland based on GF-3 fully polarimetric SAR data[J]. Remote Sensing for Natural Resources, 2021, 33(4): 105-110.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2020353     OR     https://www.gtzyyg.com/EN/Y2021/V33/I4/105
Fig.1  Pre-processed full-pol SAR image from GF-3 satellite (HH polarization)
Fig.2  Flow chart of research methods
一级分类 二级分类 主要特征
天然湿地 芦苇沼泽 以芦苇为主要覆盖植被的沼泽化草甸
翅碱蓬滩涂 以翅碱蓬为主要覆盖植被的沿海滩涂
淤泥质海滩 滨海光滩和河漫滩
自然水域 天然的浅海水域和河流
人工湿地 水稻田 以水稻种植为主的蓄水农田
养殖池塘 鱼虾蟹贝养殖区
非湿地 建筑用地 居民地和工业用地
Tab.1  Remote sensing classification system of the research area
Fig.3  False color images of polarization decomposition features
目标分解方法 极化参数
Krogager 球分量 K s 螺旋体分量 K h 二面角分量 K d
Pauli[12] 奇次散射 P a 偶次散射 P b 二面角散射 P c
Huynen[11] 目标对称因子 A 0 目标非对称性因子 B 0-B 目标非规则性因子 B 0+B
Cloude[13,14,15,16] 散射熵H 平均散射角 α - 反熵A
Freeman[17,18,19] 单次散射Odd 二次散射Dbl 体散射Vol
Tab.2  Polarization decomposition features
Fig.4  Columnar chart of SI of different objects in the research area
Fig.5  Classification result
类别 芦苇沼泽 翅碱蓬滩涂 淤泥质海滩 自然水域 水稻田 养殖池塘 建筑用地 合计 用户精度/%
芦苇沼泽 20 178 952 843 344 1 285 355 257 24 214 83.33
翅碱蓬滩涂 1 057 9 105 1 087 102 606 83 107 12 147 74.96
淤泥质海滩 583 992 10 423 690 522 627 15 13 852 75.25
自然水域 160 601 861 15 948 87 1 984 63 19 704 80.94
水稻田 2 359 989 1 405 397 10 685 81 632 16 548 64.57
养殖池塘 703 382 540 1 452 118 5 749 259 9 203 62.47
建筑用地 344 30 13 8 246 136 2 833 3 610 78.47
合计 25 384 13 051 15 172 18 941 13 549 9 015 3 066 99 278
生产精度/% 79.49 69.76 68.70 84.20 78.86 63.77 92.40
总体精度=75.47% Kappa=0.70
Tab.3  The confusion matrix of the classification result
[1] 刘润红, 梁士楚, 赵红艳, 等. 中国滨海湿地遥感研究进展[J]. 遥感技术与应用, 2017,32(6):998-1011.
[1] Liu R H, Liang S C, Zhao H Y, et al. Progress of Chinese coastal wetland based on remote sensing[J]. Remote Sensing Technology and Application, 2017,32(6):998-1011.
[2] Schmitt A, Brisco B, Kaya S, et al. Polarimetric change detection for wetlands[C]//Neale C,Cosh M.Remote Sensing and Hydrology.Oxford:IAHS Publication, 2012:375-379.
[3] Touzi R, Deschamps A, Rother G. Wetland characterization using polarimetric Radarsat-2 capability[J]. Canadian Journal of Remote Sensing, 2007,33(s1):56-67.
[4] Touzi R, Deschamps A, Rother G. Phase of target scattering for wetland characterization using polarimetric C-band SAR[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009,47(9):3241-3261.
doi: 10.1109/TGRS.2009.2018626 url: http://ieeexplore.ieee.org/document/5067298/
[5] 陈媛媛, 何秀凤, 王静. 基于SVM的极化SAR沿海滩涂分类[J]. 地理空间信息, 2015,13(6):150-153,16.
[5] Chen Y Y, He X F, Wang J. Polarimetric SAR classification of coastal wetland based on SVM[J]. Geospatial Information, 2015,13(6):150-153,16.
[6] 亓宁轩, 罗征宇, 李彬. 基于多波段全极化SAR影像的湿地分类[J]. 测绘与空间地理信息, 2017,40(1):171-174.
[6] Qi N X, Luo Z Y, Li B. Multi-band polarization SAR wetlands classification[J]. Geomatics and Spatial Information Technology, 2017,40(1):171-174.
[7] 徐梦竹, 徐佳, 邓鸿儒, 等. 基于全极化SAR影像的海岛地物分类[J]. 遥感技术与应用, 2019,34(3):647-654.
[7] Xu M Z, Xu J, Deng H R, et al. Land-use classification of islands based on fully polarimetric SAR data[J]. Remote Sensing Technology and Application, 2019,34(3):647-654.
[8] 王超, 张红, 陈曦, 等. 全极化合成孔径雷达图像处理[M]. 北京: 科学出版社, 2008:44-106.
[8] Wang C, Zhang H, Chen X, et al. Processing of fully polarimetric synthetic aperture Radar imagery[M]. Beijing: Science Press, 2008:44-106.
[9] 国家林业局《湿地公约》履约办公室. 湿地公约履约指南[M]. 北京: 中国林业出版社, 2001.
[9] Performance Office of China Convention on Wetlands. Guide on implementing ramsar convention in China[M]. Beijing: China Forestry Publishing House, 2001.
[10] 牟晓杰, 刘兴土, 阎百兴, 等. 中国滨海湿地分类系统[J]. 湿地科学, 2015,13(1):19-26.
[10] Mou X J, Liu X T, Yan B X, et al. Classification system of coastal wetlands in China[J]. Wetland Science, 2015,13(1):19-26.
[11] Huynen J R. Phenomenological theory of Radar targets[J]. Electromagnetic Scattering, 1978:653-712.
[12] 宋瑞超, 赵国忱, 卜丽静. 基于多极化特征和纹理特征的PolSAR图像分类[J]. 城市勘测, 2019(3):121-126,130.
[12] Song R C, Zhao G C, Bu L J. PolSAR images classification based on multi-polarization feature and texture feature[J]. Urban Geotechnical Investigation and Surveying, 2019(3):121-126,130.
[13] Cloude S R. Target decomposition theorems in Radar scattering[J]. Electronics Letters, 1985,21(1):22-24.
doi: 10.1049/el:19850018 url: https://digital-library.theiet.org/content/journals/10.1049/el_19850018
[14] Cloude S R, Pottier E. A review of target decomposition theorems in Radar polarimetry[J]. IEEE Transactions on Geoscience and Remote Sensing, 1996,34(2):498-518.
doi: 10.1109/36.485127 url: http://ieeexplore.ieee.org/document/485127/
[15] Cloude S R, Pottier E. An entropy based classification scheme for land applications of polarimetric SAR[J]. IEEE Transactions on Geoscience and Remote Sensing, 1997,35(1):68-78.
doi: 10.1109/36.551935 url: http://ieeexplore.ieee.org/document/551935/
[16] Cloude S R, Papathanassiou K P. Polarimetric SAR interferometry[J]. IEEE Transactions on Geoscience and Remote Sensing, 1998,36(5):1551-1565.
doi: 10.1109/36.718859 url: http://ieeexplore.ieee.org/document/718859/
[17] Freeman A, Durden S L. A three-component scattering model for polarimetric SAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 1998,36(3):963-973.
doi: 10.1109/36.673687 url: http://ieeexplore.ieee.org/document/673687/
[18] 赵泉华, 胡广臣, 李晓丽, 等. 基于全极化SAR影像的双台河口湿地分类及其变化分析[J]. 环境科学研究, 2019,32(2):309-316.
[18] Zhao Q H, Hu G C, Li X L, et al. Full-polSAR image based on wetland classification and change analysis of the Shuangtai estuary wetland[J]. Research of Environmental Sciences, 2019,32(2):309-316.
[19] 万剑华, 张乃心, 任广波, 等. 典型滨海湿地植被全极化SAR显著性特征分析与融合分类[J]. 测绘地理信息, 2018,43(5):4-8.
[19] Wan J H, Zhang N X, Ren G B, et al. Analysis and classification of fully-polarization SAR characteristics of typical vegetation in coastal wetland[J]. Journal of Geomatics, 2018,43(5):4-8.
[20] 李平, 徐新, 董浩, 等. 利用可分性指数的极化SAR图像特征选择与多层SVM分类[J]. 计算机应用, 2018,38(1):132-136,170.
[20] Li P, Xu X, Dong H, et al. Polarimetric SAR image feature selection and multi-layer SVM classification using divisibility index[J]. Journal of Computer Applications, 2018,38(1):132-136,170.
[21] 田旸. 基于Radarsat-2时间序列的湿地水文情势遥感监测与湿地分类[D]. 哈尔滨:哈尔滨师范大学, 2017.
[21] Tian Y. Monitoring hydrological regime and classifying the wetland based on time series Radarsat-2 images[D]. Harbin:Harbin Normal University, 2017.
[22] 潘庆榜. 兼容光学、雷达与地形辅助数据的森林湿地遥感分类[D]. 哈尔滨:哈尔滨师范大学, 2017.
[22] Pan Q B. Remote sensing classification in forest wetland compatible with the optical,Radar and terrain aided data[D]. Harbin:Harbin Normal University, 2017.
[23] 黄瑾. 基于多波段多极化SAR数据的黄河口湿地分类研究[D]. 青岛:中国石油大学, 2011.
[23] Huang J. Classification of the Yellow River estuary wetland based on multiband and multi-polarization SAR data[D]. Qingdao:China University of Petroleum, 2011.
[1] WAN Jianhua, LI Mei, REN Guangbo, MA Yi. Efficient method for updating coastal wetland map based on change detection technology[J]. REMOTE SENSING FOR LAND & RESOURCES, 2013, 25(4): 85-90.
[2] LIU Chun-Yue, ZHANG Shu-Qing, JIANG Hong-Xing, WANG Hui, SUN Yan. SPATIO-TEMPORAL DYNAMICS OF COASTAL WETLAND
LANDSCAPE PATTERNS IN YANCHENG, JIANGSU PROVINCE[J]. REMOTE SENSING FOR LAND & RESOURCES, 2009, 21(3): 78-83.
Viewed
Full text


Abstract

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