Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (2): 372-380    DOI: 10.11873/j.issn.1004-0323.2021.2.0372
农业遥感专栏     
基于SAR纹理信息的农作物识别研究——以农安县为例
王晨丞1(),王永前1,王利花1,2()
1.成都信息工程大学 资源环境学院,四川 成都 610225
2.重庆市气象科学研究所,重庆 401147
Crop Identification based on SAR Texture Information: A Case Study of Nong’an County
Chencheng Wang1(),Yongqian Wang1,Lihua Wang1,2()
1.Chengdu University of Information Technology,College of Resources and Environment,Chengdu 610225,China
2.Chongqing Institute of Meteorological Sciences,Chongqing 401147,China
 全文: PDF(7415 KB)   HTML
摘要:

以吉林省农安县为研究区,以Sentinel-1B双极化数据为数据源,提取出典型农作物玉米、大豆、水稻的多个纹理特征值,筛选出最佳农作物识别纹理信息参数,结合eCognition软件中的规则库,充分挖掘SAR数据中农作物纹理特征包含的属性信息,构建决策树,基于面向对象分类方法对典型农作物进行提取,通过SAR农作物提取结果的分析,获得研究区农作物最佳分类时相及最佳农作物识别纹理信息组合,对各典型农作物进行分类制图,探讨基于SAR影像后向散射特征提高农作物识别精度的可行性。结果表明:SAR数据相对于光学数据,能提供更丰富的农作物纹理信息,选取合适的纹理信息作为分类辅助数据,可以有效解决光学数据中“异物同谱”现象,提高农作物识别精度,对于研究区农作物提取贡献最大的3种SAR纹理特征依次为:均值、方差和相异性。

关键词: Sentinel?1B双极化SAR数据面向对象分类决策树纹理特征    
Abstract:

Taking Nanning County of Jilin Province as the research area, using Sentinel-1B dual polarization data as data source, multiple texture eigenvalues of typical crops such as corn, soybean and rice were extracted, and the best crop identification parameters were selected. Combined with eCognition software The rule base in the model fully mines the attribute information contained in the texture features of crops in SAR data, constructs a decision tree, extracts typical crops based on object-oriented classification methods, and obtains the optimal classification phase of crops in the study area through the analysis of SAR crop extraction results. And the best crop identification texture information combination, classify and map each typical crop, and explore the feasibility of improving the accuracy of crop identification based on the back-scattering characteristics of SAR images. The results show that SAR data can provide richer crop texture information than optical data. Selecting suitable texture information as auxiliary data for classification can effectively solve the phenomenon of "foreign matter homology" in optical data and improve the accuracy of crop identification. The three SAR texture features that contribute the most to crop extraction are: mean, variance, and dissimilarity.

Key words: Sentinel-1B    Dual polarization SAR    Object-oriented classification    Decision tree    Texture feature
收稿日期: 2019-10-09 出版日期: 2021-05-24
ZTFLH:  TN958  
基金资助: 中国气象局省所科技创新发展专项(SSCX2020CQ);重庆市气象部门业务技术攻关项目(YWJSGG-202017);重庆市技术创新与应用发展专项(cstc2020jscx-msxmX0193);中国博士后科学基金(2020M683258);四川省科技计划项目(2018JY0484)
通讯作者: 王利花     E-mail: ccw0280@gmail.com;70674743@qq.com
作者简介: 王晨丞(1996-),男,四川达州人,硕士研究生,主要从事卫星遥感应用研究。E?mail: ccw0280@gmail.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  
王晨丞
王永前
王利花

引用本文:

王晨丞,王永前,王利花. 基于SAR纹理信息的农作物识别研究——以农安县为例[J]. 遥感技术与应用, 2021, 36(2): 372-380.

Chencheng Wang,Yongqian Wang,Lihua Wang. Crop Identification based on SAR Texture Information: A Case Study of Nong’an County. Remote Sensing Technology and Application, 2021, 36(2): 372-380.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.2.0372        http://www.rsta.ac.cn/CN/Y2021/V36/I2/372

作物4月5月6月7月8月9月10月
玉米播种出叶拔节吐丝乳熟吐丝乳熟收获
大豆播种分枝结荚鼓粒结荚鼓粒收获
水稻播种移栽出叶拔节抽穗乳熟抽穗成熟收获
表1  主要农作物物候期
图像ID数据等级波段极化方式入射角/°
S1B_IW_GRDH_1SDV_20170523T214531L1 GRDCVV/VH30~46
S1B_IW_GRDH_1SDV_20170616T214532L1 GRDCVV/VH30~46
S1B_IW_GRDH_1SDV_20170710T214534L1 GRDCVV/VH30~46
S1B_IW_GRDH_1SDV_20170815T214535L1 GRDCVV/VH30~46
S1B_IW_GRDH_1SDV_20170920T214537L1 GRDCVV/VH30~46
表2  数据参数信息
图1  采样点分布图
图2  典型农作物VH极化后向散射系数时间序列图
图3  均值折线图
图4  协同性折线图
图5  方差折线图
图6  对比度折线图
图7  相异性折线图
图8  信息熵折线图
时相作物名称采样点个数/个正确识别个数/个识别精度 /%
2017年5月23日玉米111090.91
大豆6466.67
水稻600
2017年6月16日玉米11872.73
大豆6233.33
水稻6466.67
2017年7月10日玉米11654.55
大豆6350
水稻6583.33
2017年8月15日玉米11763.64
大豆6466.67
水稻6466.67
2017年9月20日玉米11981.82
大豆6233.33
水稻66100
表3  农作物识别精度评价表
图9  Sentinel-1B SAR 2017年5-9月农作物识别结果
1 Lintz J, Simonett D S. Sensors for Spacecraft[J]. Remote Sensing of Environment Reading,1976(1):323-343.
2 Cloude S R, Pottier E. An Entropy based Classification Scheme for Land Applications of Polarimetric SAR[J]. IEEE Transactions on Geoscience & Remote Sensing,1997,35(1):68-78.
3 Lee J S, Grunes M R, Ainsworth T L, et al. Unsupervised Classification Using Polarimetric Decomposition and the Complex Wishart Classifier[J]. IEEE Transactions on Geoscience & Remote Sensing, 2002, 37(5):2249-2258.
4 Mcnairn H, Sanden J J V D, Brown R J, et al. The Potential of RadarSat-2 for Crop Mapping and Assessing Crop Condition[J]. Japanese Journal of Radiological Technology, 2000, 49(2):69-72.
5 Skriver H. Crop Classification by Multitemporal C- and L-Band Single- and Dual-Polarization and Fully Polarimetric SAR[J]. IEEE Transactions on Geoscience & Remote Sensing, 2012, 50(6):2138-2149.
6 Skakun S, Kussul N, Shelestov A Y, et al. Efficiency Assessment of Multitemporal C-Band Radarsat-2 Intensity and Landsat-8 Surface Reflectance Satellite Imagery for Crop Classification in Ukraine[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(8):3712-3719.
7 Dong Zhaoxia. Dryland Crop Identification and Biological Parameters Estimation based on Full-Polarization SAR Data[D].Beijing:Chinese Academy of Agricultural Sciences,2016.
7 东朝霞. 基于全极化SAR数据的旱地作物识别与生物学参数反演研究[D]. 北京:中国农业科学院,2016.
8 Zhang Pingping, Shen Shuanghe, Li Bingbai,et al. Analysis of Polarization Scattering Characteristics of Rice and Classification of Rice Fields[J]. Jiangsu Agricultural Sciences, 2006(1):148-152.张萍萍, 申双和, 李秉柏,等. 水稻极化散射特征分析及稻田分类方法研究[J]. 江苏农业科学, 2006(1):148-152.
9 Xu Jin, An Yulun, Liu Suihua, et al. Discussion on Classification for Sentinel-1A SAR Data in Mountainous Plateau based on Backscatter Features: A Case Study in Anshun City[J]. Journal of Guizhou Normal University(Natural Sciences), 2016, 34(6):15-19.
9 许璟, 安裕伦, 刘绥华,等. 基于Sentinel-1A后向散射特性的高原山区地物分类探讨——以安顺市为例[J]. 贵州师范大学学报(自然版), 2016, 34(6):15-19.
10 Yang Zhi. Rice Phenology Estimation and Parameter Retrieval based on Polarimetric Synthetic Aperture Radar(SAR)[D]. Beijing:The University of Chinese Academy of Sciences(Institute of Remote Sensing and Digital Earth), 2017.
10 杨知. 基于极化SAR的水稻物候期监测与参数反演研究[D]. 北京:中国科学院大学(中国科学院遥感与数字地球研究所), 2017.
11 Zhou Tao, Pan Jianjun, Han Tao, et al. Planting Area Extraction of Winter Wheat based on Multi-temporal SAR Data and Optical Imagery[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(10):215-221.
11 周涛,潘剑君,韩涛,等.基于多时相合成孔径雷达与光学影像的冬小麦种植面积提取[J].农业工程学报,2017,33(10):215-221.
12 Yang Shenbin, Li Bingbai, Shen Shuanghe, et al. Rice Monitoring based on ENVISAT ASAR Data[J]. Jiangsu Journal of Agricultural Sciences,2008,24(1):33-38.
12 杨沈斌,李秉柏, 申双和,等.基于ENVISAT ASAR数据的水稻遥感监测[J].江苏农业学报,2008,24(1):33-38.
13 Xu Mengzhu, Xu Jia, Deng Hongru, et al. Land-use Classification of Islands based on Fully Polarimetric SAR Data[J]. Remote Sensing Technology and Application, 2019, 34(3): 647-654.
13 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): 657-654.
14 Wang Fang, Sun Guoqing, Wu Xuerui. Application a Coherent Vegetation Backscattering Model to Corn Field and Comparison with ENVISAT ASAR Data[J]. Journal of Beijing Normal University(Natural Science), 2008, 44(2):203-206.
14 王芳, 孙国清, 吴学睿. 基于相干植被模型和ASAR数据的玉米地后向散射特征研究[J]. 北京师范大学学报(自然科学版), 2008, 44(2):203-206.
15 Hua Guoqiang, Xiao Jing, Huang Xiaojun, et al. Analysis of Corn Backscattering Characteristics Based on Full Polarization SAR Data[J]. Jiangsu Agricultural Sciences, 2011, 39(3):562-565.
15 化国强, 肖靖, 黄晓军,等. 基于全极化SAR数据的玉米后向散射特征分析[J]. 江苏农业科学, 2011, 39(3):562-565.
16 Wang Qing, Zeng Qiming, Liao Jingjuan. Feature Extraction and Classification of SAR Image based on Target Decomposition and Scattering Mechanism Index[J]. Remote Sensing Information, 2012(2):9-14.
16 王庆, 曾琪明, 廖静娟. 基于特征向量分解与散射机制判别指数的全极化SAR图像地物提取与分类[J]. 遥感信息, 2012(2):9-14.
17 Zhu Junjie, Guo Huadong, Fan Xiangtao, et al. Research on Texture Classification of Single-band Single-polarized High-resolution SAR Image[J]. Remote Sensing for Land & Resources, 2005, 17(2):36-39.
17 朱俊杰, 郭华东, 范湘涛,等. 单波段单极化高分辨率SAR图像纹理分类研究[J]. 国土资源遥感, 2005, 17(2):36-39.
18 Chen Fulong,Wang Chao, Zhang Hong. Improved Maximum Likelihood Remote Sensing Image Classification Method: Taking SAR Image as an Example[J]. Remote Sensing for Land and Resources, 2008, 20(1):75-78.
18 陈富龙, 王超, 张红. 改进最大似然遥感影像分类方法——以SAR影像为例[J]. 国土资源遥感, 2008, 20(1):75-78.
19 Ding Yaping. Dryland Crop Classification and Acreage Estimation based on Microwave Remote Sensing[D]. Beijing: Chinese Academy of Agricultural Sciences,2013.
19 丁娅萍. 基于微波遥感的旱地作物识别及面积提取方法研究[D]. 北京:中国农业科学院, 2013.
20 Yang Yufeng. Research on Classification Methods of Fully Polarimetric SAR Image based on Target Decomposition Theory[D]. Nanjing: Nanjing Forestry University, 2016.
20 杨玉锋. 基于目标分解的全极化SAR图像分类方法研究[D]. 南京:南京林业大学, 2016.
21 Gao Han, Wang Changcheng, Yang Minhua, et al. Scattering Feature Analysis and Classification of Crops based on GF-3 Polsar Data[J]. Engineering of Surveying and Mapping, 2019, 28(3): 50-56.
21 高晗, 汪长城, 杨敏华, 等. 基于高分三号极化SAR数据的农作物散射特性分析及分类[J]. 测绘工程, 2019, 28(3): 50-56.
22 Zhao Hongwei, Chen Zhongxin, Jiang Hao, et al. Early Growing Stage Crop Species Identification in Southern China based on Sentinel-1A Time Series Imagery and One-Dimensional CNN[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(3): 169-177.
22 赵红伟, 陈仲新, 姜浩, 等. 基于Sentinel-1A影像和一维CNN的中国南方生长季早期作物种类识别[J]. 农业工程学报, 2020, 36(3): 169-177.
23 He Yanfen, Zhang Bai, Ma Chaoqun. Effects of Landscape on Draught Occurrences in the Songnen Plain: A Case Study Using Nong'an County as Its Subject[J]. Agricultural Research in the Arid Areas,2005,23(1):172-178.
23 何艳芬, 张柏, 马超群. 松嫩平原土地景观动态对旱灾的影响研究——以吉林省农安县为例[J]. 干旱地区农业研究, 2005, 23(1):172-178.
24 Wang Di, Zhou Qingbo, Chen Zhongxin , et al. Reseach Advances on Crop Identification Using Synthetic Aperture Radar[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(16):203-212.
24 王迪, 周清波, 陈仲新, 等. 基于合成孔径雷达的农作物识别研究进展[J]. 农业工程学报, 2014, 30(16):203-212.
[1] 汪胜,杨晓峰,马文韬,相坤生,胡蝶. 基于星载微波亮温数据的西北太平洋热带气旋生成预测方法[J]. 遥感技术与应用, 2021, 36(1): 198-207.
[2] 郑琪,邸苏闯,潘兴瑶,刘洪禄,朱永华,张岑,周星. 基于Rapid Eye数据的北京生态涵养区土地利用分类及变化研究[J]. 遥感技术与应用, 2020, 35(5): 1118-1126.
[3] 牟昱璇,邬明权,牛铮,黄文江,杨尽. 南方地区复杂条件下的耕地面积遥感提取方法[J]. 遥感技术与应用, 2020, 35(5): 1127-1135.
[4] 李强,冯德俊,瑚敏君,伍燚垚,杨历辉. 集成特征分量的高分二号影像阴影检测[J]. 遥感技术与应用, 2019, 34(6): 1252-1260.
[5] 徐凡, 张雪红, 石玉立. 基于激光雷达和航拍影像的城市地物分类研究[J]. 遥感技术与应用, 2019, 34(2): 253-262.
[6] 李晓慧, 王宏, 李晓兵, 迟登凯, 汤曾伟, 韩重远. 基于多时相Landsat 8 OLI影像的农作物遥感分类研究[J]. 遥感技术与应用, 2019, 34(2): 389-397.
[7] 谷晓天, 高小红, 马慧娟, 史飞飞, 刘雪梅, 曹晓敏. 复杂地形区土地利用/土地覆被分类机器学习方法比较研究[J]. 遥感技术与应用, 2019, 34(1): 57-67.
[8] 王常颖, 田德政, 韩园峰, 隋毅, 初佳兰. 基于属性差决策树的全极化SAR影像海冰分类[J]. 遥感技术与应用, 2018, 33(5): 975-982.
[9] 江东,陈帅,丁方宇,付晶莹,郝蒙蒙. 基于面向对象的遥感影像分类研究——以河北省柏乡县为例[J]. 遥感技术与应用, 2018, 33(1): 143-150.
[10] 王凯,赵军,朱国锋. 基于GF-1遥感数据决策树与混合像元分解模型的冬小麦种植面积早期估算[J]. 遥感技术与应用, 2018, 33(1): 158-167.
[11] 周晓宇,陈富龙. 四川大熊猫栖息地PALSAR时序数据森林覆盖动态监测研究[J]. 遥感技术与应用, 2017, 32(6): 1100-1106.
[12] 姬忠林,张月平,李乔玄,刘绍贵,李淑娟,任红艳. 基于GF-1影像的冬小麦和油菜种植信息提取[J]. 遥感技术与应用, 2017, 32(4): 760-765.
[13] 吕利利,颉耀文,黄晓君,张秀霞,李汝嫣. 基于CART决策树分类的沙漠化信息提取方法研究[J]. 遥感技术与应用, 2017, 32(3): 499-506.
[14] 朱钟正,陈玉福,朱文泉,郑周涛. 适用于多目标遥感自动解译的最佳专题指数筛选[J]. 遥感技术与应用, 2017, 32(3): 564-574.
[15] 郝泷,陈永富,刘华,朱雪林,达哇扎西,李伟娜. 基于纹理信息CART决策树的林芝县森林植被面向对象分类[J]. 遥感技术与应用, 2017, 32(2): 386-394.