Fine classification of rice with multi-temporal compact polarimetric SAR based on SVM+SFS strategy

doi:10.6046/gtzyyg.2018.04.04

Abstract
Figures/Tables
References
Related Articles
Metrics

Download: PDF(4445 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Different types and planting methods can result in the discrepancy of rice growth and yield. It is of great importance to provide accurate growth vigor information for rice growth monitoring and estimation using fine distinction of different rice varieties and planting methods. As a new type of SAR sensor, compact polarimetry synthetic aperture Radar (CP-SAR) provides the possibility for the fine mapping of paddy land with abundant polarimetric information and large width. In this study, the authors firstly used RADARSAT-2 fully polarimetric SAR data to simulate CP-SAR data and extracted 22 types of feature parameters. In addition, on the basis of the multi-dimensional feature information CP - SAR data, the support vector machine and sequential forward selection (SVM + SFS) strategy were performed for feature selection, and the optimal feature subset of paddy land fine classification was obtained. Moreover, the decision tree and SVM method were used for paddy land fine classification based on feature subset. The results show that paddy land fine classification method based on decision tree can achieve better classification results. The overall classification precision and Kappa coefficient of optimal feature subset respectively are 92.57% and 0.896, which are higher than those of the set of all feature parameters by improving 1.2% in overall classification precision and 0.016 in Kappa coefficient.

Keywords CP-SAR SVM+SFS paddy land decision tree classification multi-temporal

TP79

Corresponding Authors: Kun LI E-mail: likun@radi.ac.cn

Issue Date: 07 December 2018

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	Xianyu GUO
	Kun LI
	Zhiyong WANG
	Hongyu LI
	Zhi YANG

Cite this article:

Xianyu GUO,Kun LI,Zhiyong WANG, et al. Fine classification of rice with multi-temporal compact polarimetric SAR based on SVM+SFS strategy[J]. Remote Sensing for Land & Resources, 2018, 30(4): 20-27.

URL:

https://www.gtzyyg.com/EN/10.6046/gtzyyg.2018.04.04 OR https://www.gtzyyg.com/EN/Y2018/V30/I4/20

Fig.1 Three kinds of paddy land characteristics in different phonological stages

Fig.2 Color synthetic images of CP-SAR data in different polarization channels

Fig.3 Flow chart of technology

符号		参数名称		参数物理意义	公式
$g = [g 0, g 1, g 2, g 3] T$		Stokes矢量		表征散射回波强度和极化状态	文献[19]公式2
$σ 0 RH$ $σ 0 RV$ $σ 0 RL$ $σ 0 RR$		RH,RV,RL,RR极化后向散射系数		表征目标在RH,RV,RL,RR极化的回波强度	$σ 0 RH = [1,1, 0,0] · g$ $σ 0 RV = [1, - 1,0, 0] · g$ $σ 0 RL = [1,0, 0,1] · g$ $σ 0 RR = [1,0, 0, - 1] · g$
$δ$		RH和RV相位角		RH和RV极化散射回波之间的相对相位角	$δ = arctan (g 3 / g 2)$
$m - δ_db$ $m - δ_vol$ $m - δ_s$		$m - δ$ 分解二次散射、体散射和面散射		表征地物二次散射、体散射和面散射	文献[20]公式7
$m - χ_db$ $m - χ_vol$ $m - χ_s$		$m - χ$ 分解二次散射 $、$ 体散射和面散射		表征地物二次散射、体散射和面散射	文献[19]公式5
$μ C$		圆极化比		Stokes向量派生参数	$μ C = (g 0 - g 3) / (g 0 + g 3)$
$μ$		一致性系数		与目标散射机理有关	$μ = 2 Im < s RH s * RV > < s RH s * RV > + < s RH s * RV >$ , $式中 : s RH$ 和 $s RV$ 分别为极化散射矩阵元素; Im 表示取复数的虚部; <>表示内积运算; *表示复共轭
$m$		极化度		表征目标散射回波去相关程度	$m = g 12 + g 22 + g 32 g 0, 0 < m < 1$
$ρ$		RH-RV相关系数		表征散射矩阵元素 $s RH$ 和 $s RV$ 的相关性	$ρ = < \| s RH s * RV \| > < s RH s * RV > + < \| s RH s * RV \| >$
$α$		平均散射角		与目标散射机理有关	$α = 12 arctan [g 12 + g 22 / (± g 3)]$
$H i$		香农熵		表征相干矩阵的强度	$H i = 3 lg πetr [T] 3$ , $式中 : T$ 为3×3相干矩阵; $tr [T]$ 表示相干矩阵 $T$ 的迹
符号	参数名称		参数物理意义			公式
$H p$	香农极化度		表征Bakarat( $p T$ )的极化度, $p T = 1 - 27 det [T] tr [T] 3$ 式中 $det [T]$ 表示 $T$ 的行列式值			$H p = lg 27 det [T] tr [T] 3$

Tab.1 Twenty two CP characteristic parameters

影像日期	CP-SAR特征参数
2012年6月27日	$μ$ , $δ$ , $α$ , $m - δ_db$ , $g 0, g 3$ , $σ 0 RL$ , $σ 0 RV$ , $σ 0 RH$ , $σ 0 RR$ , $m - δ_vol$ , $m - χ_vol$
2012年7月11日	$m - χ_s$ , $σ 0 RL$ , $σ 0 RV$ , $σ 0 RH$ , $m - δ_vol$ , $H i$ , $g 1, m - χ_vol$
2012年7月21日	$δ$ , $σ 0 RL$ , $σ 0 RV$ , $σ 0 RH$ , $σ 0 RR$ , $g 0$ , $m - χ_s$ , $μ C$

Tab.2 Optimal CP-SAR characteristic parameters by SVM + SFS

Fig.4 Intensity and non-intensity polarization characteristic parameters about three kinds of paddy land

Fig.5 Classification decision tree of three kinds of paddy land

Fig.6 Polarimetric parameters in different surface features

Tab.3 Comparison of classification accuracy between the two methods

Fig.7 Classification results of 28 parameters at three periods

[1]	郭华东, 李新武 . 新一代SAR对地观测技术特点与应用拓展[J]. 科学通报, 2011,56(15):1155-1168.
[1]	Guo H D, Li X W . Technical characteristics and potential application of the new generation SAR for earth observation[J]. Chinese Science Bulletin, 2011,56(15):1155-1168.
[2]	Souyris J C, Imbo P, Fjortoft R , et al. Compact polarimetry based on symmetry properties of geophysical media:The /spl pi//4 mode[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005,43(3):634-646. doi: 10.1109/TGRS.2004.842486 url: http://ieeexplore.ieee.org/document/1396337/
[3]	Raney R K . Dual-polarized SAR and stokes parameter[J]. IEEE Geoscience and Remote Sensing Letters, 2006,3(3):317-319. doi: 10.1109/LGRS.2006.871746 url: http://ieeexplore.ieee.org/document/1657996/
[4]	Raney R K . Hybrid-polarity SAR architecture[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007,45(11):3397-3404. doi: 10.1109/TGRS.2007.895883 url: http://ieeexplore.ieee.org/document/4358849/
[5]	Collins M J, Denbina M, Atteia G .On the reconstruction of quad-pol SAR data from compact polarimetry data for ocean target detection[J].IEEE Transactions on Geoscience and Remote Sensing 2013,(51) 1:591-600. doi: 10.1109/TGRS.2012.2199760 url: http://ieeexplore.ieee.org/document/6227345/
[6]	张红, 谢镭, 王超 , 等. 简缩极化SAR数据信息提取与应用[J]. 中国图象图形学报, 2013,18(9):1065-1073.
[6]	Zhang H, Xie L, Wang C , et al. Information extraction application of compact polarimetric SAR data[J]. Journal of Image and Graphics, 2013,18(9):1065-1073.
[7]	Ainsworth T L, Kelly J P, Lee J S . Classification comparisons between dual-pol,compact polarimetric and quad-pol SAR imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2009,64(5):464-471. doi: 10.1016/j.isprsjprs.2008.12.008 url: http://linkinghub.elsevier.com/retrieve/pii/S0924271609000069
[8]	Garestier F , Dubois-Fernandez P C,Papathanassiou K.Pine forest height inversion using single-pass X-band PolInSAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008,46(1):59-68. doi: 10.1109/TGRS.2007.907602 url: http://ieeexplore.ieee.org/document/4384457/
[9]	Zhang X, Dierking W, Zhang J , et al. Retrieval of the thickness of undeformed sea ice from simulated C-band compact polarimetric SAR images[J]. The Cryosphere, 2016,10(5):1529-1545. doi: 10.5194/tc-10-1529-2016 url: https://www.the-cryosphere.net/10/1529/2016/
[10]	Truongloi M L, Freeman A, Dubois-Fernandez P C , et al. Estimation of soil moisture and Faraday rotation from bare surfaces using compact polarimetry[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009,47(11):3608-3615. doi: 10.1109/TGRS.2009.2031428 url: http://ieeexplore.ieee.org/document/5280343/
[11]	Choudhury I, Chakraborty M . SAR signature investigation of rice crop using RADARSAT data[J]. International Journal of Remote Sensing, 2006,27(3):519-534. doi: 10.1080/01431160500239172 url: https://www.tandfonline.com/doi/full/10.1080/01431160500239172
[12]	Bouvet A, Toan T L . Use of ENVISAT/ASAR wide swath data for timely rice fields mapping in the Mekong River Delta[J]. Remote Sensing of Environment, 2011,115(4):1090-1101. doi: 10.1016/j.rse.2010.12.014 url: https://linkinghub.elsevier.com/retrieve/pii/S0034425710003603
[13]	Bouvet A, Toan T L, Lam-Dao N . Monitoring of the rice cropping system in the Mekong Delta using ENVISAT/ASAR dual polarization data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009,47(2):517-526. doi: 10.1109/TGRS.2008.2007963 url: http://ieeexplore.ieee.org/document/4768722/
[14]	Li K, Zhang F, Shao Y , et al. Polarization signature analysis of paddy rice in southern China[J]. Canadian Journal of Remote Sensing, 2011,37(1):122-135. doi: 10.5589/m11-018 url: http://www.tandfonline.com/doi/abs/10.5589/m11-018
[15]	Li K, Brisco B, Yun S , et al. Polarimetric decomposition with RADARSAT-2 for rice mapping and monitoring[J]. Canadian Journal of Remote Sensing, 2012,38(2):169-179. doi: 10.5589/m12-024 url: http://www.tandfonline.com/doi/abs/10.5589/m12-024
[16]	Brisco B, Li K, Tedford B , et al. Compact polarimetry assessment for rice and wetland mapping[J]. International Journal of Remote Sensing, 2013,34(6):1949-1964. doi: 10.1080/01431161.2012.730156 url: https://www.tandfonline.com/doi/full/10.1080/01431161.2012.730156
[17]	Uppala D, Kothapalli R V, Poloju S , et al. Rice crop discrimination using single date RISAT1 Hybrid (RH,RV) polarimetric data[J]. Photogrammetric Engineering and Remote Sensing, 2015,81(7):557-563. doi: 10.14358/PERS.81.7.557 url: http://openurl.ingenta.com/content/xref?genre=article&issn=0099-1112&volume=81&issue=7&spage=557
[18]	吴永辉, 计科峰, 郁文贤 . SVM全极化SAR图像分类中的特征选择[J]. 信号处理, 2007,23(6):877-881. doi: 10.3969/j.issn.1003-0530.2007.06.019 url: http://www.cqvip.com/Main/Detail.aspx?id=26418335
[18]	Wu Y H, Ji K F, Yu W X . A new feature selection algorithm for SVM-based fully polarimetric SAR image classification[J]. Signal Processing, 2007,23(6):877-881.
[19]	Raney R K, Cahill J T S, Patterson G W , et al. The m-chi decomposition of hybrid dual-polarimetric Radar data with application to lunar craters[J]. Journal of Geophysical Research Atmospheres, 2012,117(E12):5093-5096. doi: 10.1029/2011JE003986 url: http://onlinelibrary.wiley.com/doi/10.1029/2011JE003986/full
[20]	Charbonneau F J, Brisco B, Raney R K , et al. Compact polarimetry overview and applications assessment[J]. Canadian Journal of Remote Sensing, 2010,36(s2):298-315. doi: 10.5589/m10-062 url: http://www.tandfonline.com/doi/abs/10.5589/m10-062

[1]	Juan XUE, Linfeng YU, Qinan LIN, Guang LIU, Huaguo HUANG. Using Sentinel-1 multi-temporal InSAR data to monitor the damage degree of shoot beetle in Yunnan pine forest[J]. Remote Sensing for Land & Resources, 2018, 30(4): 108-114.
[2]	ZHANG Zhaoying, LU Yicen, WU Guozhou, WANG Yongli. Retrieval of precipitation for grassland based on the multi-temporal Sentinel-1 SAR data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(4): 156-160.
[3]	ZHOU Xiaoyu, CHEN Fulong, JIANG Aihui. SVM-based forest mapping of Wolong Giant Panda Habitat using SAR data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(3): 85-91.
[4]	WANG Jinjie, DING Jianli, ZHANG Cheng, CHEN Wenqian. Method of water information extraction by improved SWI based on GF-1 satellite image[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 29-35.
[5]	SHAO Yanpo, HONG Youtang. PIF method for relative radiometric correction of remote sensing images[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 7-13.
[6]	YANG Yuhui, YAN Meichun, LI Zhijia, YU Qing, CHEN Beibei. Classification model for "same subject with different spectra" on complicated surface in Southern hilly areas[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(2): 79-83.
[7]	GUO Hongyan, ZOU Liqun, ZHANG Youyan, LIU Yang, DONG Wentong, ZHOU Hongying. Data management of multi-temporal images for remote sensing information services in oil and gas application[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(2): 188-192.
[8]	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.
[9]	XU Chao, ZHAN Jinrui, PAN Yaozhong, ZHU Wenquan. Extraction of cropland information based on multi-temporal TM images[J]. REMOTE SENSING FOR LAND & RESOURCES, 2013, 25(4): 166-173.
[10]	SUN Ming, SHEN Wei-shou, XIE Min, LI Hai-dong, GAO Fei. The Identification of Grassland Types in the Source Region of the Yarlung Zangbo River Based on Spectral Features[J]. REMOTE SENSING FOR LAND & RESOURCES, 2012, 24(1): 83-89.
[11]	LI Min-Guang, LI Ying-Cheng, XUE Yan-Li, YE Dong-Mei. A Discussion on an Object-oriented Approach to Island Recognition Based on Multi-source and Multi-temporal Remotely Sensed Data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2010, 22(1): 65-68.
[12]	JIA Shen-Yue, XIAO Peng-Feng. THE MONITORING OF LAKE CHANGE IN SOUTH QIANGTANG AREA OF QINGHAI-TIBET PLATEAU USING MULTI-TEMPORAL TUPU[J]. REMOTE SENSING FOR LAND & RESOURCES, 2009, 21(4): 78-81.
[13]	WANG Xun, XU Dan-Dan, LI Wen-Long. IMAGE EXTRACTION OF MAQU WETLANDS AND ACCURACY ANALYSIS[J]. REMOTE SENSING FOR LAND & RESOURCES, 2009, 21(4): 96-100.
[14]	YANG Qiang, ZHANG Zhi. THE REMOTE SENSING EXTRACTION METHOD FOR THE MINING AREA AND THE SOLID WASTE IN THE BAOKANG PHOSPHORITE ORE DISTRICT, HUBEI PROVINCE[J]. REMOTE SENSING FOR LAND & RESOURCES, 2009, 21(2): 87-90.
[15]	JIN Bao-Shi, ZHOU Bao-Hua. MULTI-TEMPORAL DYNAMIC CHANGE OF THE LAKE WATER AREA IN ANQING ALONG THE YANGTZE RIVER IN THE PAST TWENTY YEARS[J]. REMOTE SENSING FOR LAND & RESOURCES, 2008, 20(3): 74-77.

Viewed

Full text

Abstract

Cited

Shared

Discussed