1. Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China 2. Land Resources Surveying and Mapping Institute of Guangxi Zhuang Autonomous Region, Nanning 530023, China 3. School of Natural Resources and Surveying, Nanning Normal University, Nanning 530001, China 4. College of Land and Resources Engineering, Kunming University of Science and Technology, Kunming 650500, China
With the purpose of exploring the extraction of early paddy rice area distribution information from bipolar Sentinel-1A Radar image data recognition and on the basis of an analysis of backscattering coefficients of typical terrain objects, the authors employed the idea that polarization differential SAR images and polarization ratio SAR images play an important role in the classification of typical terrain objects and proposed the utilization of the normalized parameters of water body. Then, the support vector machine (SVM) classification method and the threshold classification method were used to extract the area of early paddy rice from the normalized polarimetric SAR data of single-phase and multi-temporal water body on March 10, March 22, April 3, April 15 and 15 April 15 in 2017. The results show that the threshold classification method is better than the SVM classification method. The overall accuracy of the former method is 89.01%, Kappa coefficient is 0.823 1, mapping accuracy and user accuracy of early paddy rice are 92.68% and 82.26%, respectively. The planting area is 129,000 hectares, which is basically consistent with the spatial distribution of the main early paddy rice production bases in Lingao County. It can be concluded that multi-parameter polarimetric SAR data can improve the accuracy of recognition and extraction of terrain objects. The best monitoring data for extracting early paddy rice area are multi-temporal NDVH polarimetric SAR data.
刘警鉴, 李洪忠, 华璀, 孙毓蔓, 陈劲松, 韩宇. 基于Sentinel-1A数据的临高县早稻面积提取[J]. 国土资源遥感, 2020, 32(1): 191-199.
Jingjian LIU, Hongzhong LI, Cui HUA, Yuman SUN, Jinsong CHEN, Yu HAN. Extraction of early paddy rice area in Lingao County based on Sentinel-1A data. Remote Sensing for Land & Resources, 2020, 32(1): 191-199.
Shao Y, Guo H D, Fan X T , et al. Studies on rice backscatter signatures in time domain and its applications[J]. Journal of Remote Sensing, 2001,5(5):340-345.
Liu H, Shao Y, Wang C Z , et al. The application of muti-temopral RADARSAT data to paddy field classification in Zhaoqing area,Guangdong Province,China[J]. Remote Sensing for Land and Resources, 1997,9(4):1-6,13.doi: 10.6046/gtzyyg.1997.04.01.
Yang S B, Li B B, Shen S H , et al. Rice mapping research based on multi-temporal,multi-polarization backscattering differences[J]. Journal of Remote Sensing, 2008,12(4):613-619.
Guo X Y, Li K, Wang Z Y , et al. Fine classification of rice with multi-temporal compact polarimetric SAR based on SVM + SFS strategy[J]. Remote Sensing for Land and Resources, 2018,30(4):20-27.doi: 10.6046/gtzyyg.2018.04.04.
Wang D, Zhou Q B, Chen Z X , et al. Research advances on crop identification using synthetic aperture Radar[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014,30(16):203-212.
Yan X W, Cen X J, Tang Q J , et al. Studies on suitable sowing time for hybrid rice seed production in the early-cropping season in Lingao County and its surrounding area in northwestern Hainan[J]. Hybrid Rice, 2016,31(5):25-27.
Hua G Q, Li C, Yang S B , et al. Rice mapping based on ratio method using RADARSAT-2 SAR data[J]. Jiangsu Journal of Agricultural Sciences, 2012,28(6):1451-1458.
Li L, Kong Q L, Wang P X , et al. Monitoring of maize planting area based on time-series Sentinel-1A SAR data[J]. Resources Science, 2018,40(8):1608-1621.
Han D, Yang H, Yang G J , et al. Monitoring model of maize lodging based on Sentinel-1 Radar image[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018,34(3):166-172.
Zhang M, Zeng Y N . Mapping paddy fields of Dongting Lake area by fusing Landsat and MODIS data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(13):178-185.
Shao Y, Liao J J, Fan X T , et al. Analysis on rice backscatter signatures in time domain:Comparison between RADARSAT-SAR observation and simulated model results[J]. Journal of Remote Sensing, 2002,6(6):440-450.
[16]
Richards J A, Jia X P . Remote Sensing Digital Image Analysis[M]. Berlin:Springer-Verlag, 1999.
[17]
Loosvelt L, Peters J, Skriver H , et al. Random forests as a tool for estimating uncertainty at pixel-level in SAR image classification[J]. International Journal of Applied Earth Observations and Geoinformation, 2012,19(1):173-184.
Li N, Zhu X F, Pan Y Z , et al. Optimized SVM based on artificial bee colony algorithm for remote sensing image classification[J]. Journal of Remote Sensing, 2018,22(4):559-569.
Wang X Q, Wang Q M, Shi X M , et al. Rice field mapping and monitoring using ASAR data based on principal component analysis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2008,24(10):122-126.
Kong J L, Li J J, Zhen P P , et al. Inversion of soil moisture in arid area based on microwave and optical remote sensing data[J]. Journal of Geo-Information Science, 2016,18(6):857-863.