基于光谱时间序列拟合的中国南方水稻遥感识别方法研究

doi:10.3724/SP.J.1047.2017.00117

地球信息科学学报 ›› 2017, Vol. 19 ›› Issue (1): 117-124.doi: 10.3724/SP.J.1047.2017.00117

基于光谱时间序列拟合的中国南方水稻遥感识别方法研究

宋盼盼^1,²(), 杜鑫², 吴良才¹, 王红岩², 李强子^2,*^*(), 王娜^2,³

1. 东华理工大学测绘工程学院,南昌 330013
2. 中国科学院遥感与数字地球研究所,北京 100101
3. 中国科学院大学,北京 100049

收稿日期:2016-06-30 修回日期:2016-08-29 出版日期:2017-01-20 发布日期:2017-01-13
作者简介:
作者简介：宋盼盼（1990-）,男,河南开封人,硕士生,主要从事农业遥感作物分类研究。E-mail: 18511034856@163.com
基金资助:
国家自然科学基金面上项目（41571422）;国家自然科学青年基金项目（41301497）;中国科学院重点部署项目（KZZD-EW-08-05）;高分辨率对地观测系统重大专项（00-Y30B15-9001-14/16-2）

Research on the Method of Rice remote sensing Identification Based on SpectralTime-series Fitting in Southern China

SONG Panpan^1,²(), DU Xin², WU Liangcai¹, WANG Hongyan², LI Qiangzi^2,^*(), WANG Na^2,³

1. College of surveying and mapping engineering, East China Institute of Technology, Nanchang, 330013, China
2. Institute of Remote Sensing and Digital Earth, CAS, Beijing 100101, China
3. University of Chinese Academy of Sciences, Beijing 100101, China

Received:2016-06-30 Revised:2016-08-29 Online:2017-01-20 Published:2017-01-13
Contact: LI Qiangzi

摘要/Abstract

摘要：

多云多雾现象是农作物遥感分类经常遇到的问题,影响分类精度。为解决此类问题,本文提出一种基于时间序列GF-1号遥感影像识别水稻方法。利用多时相时间序列的GF-1号遥感影像提取中稻、晚稻的近红外波段（NIR）反射率、红光（R）波段反射率、归一化植被指数（NDVI）特征;拟合光谱和植被指数时间序列特征曲线;分析多时相影像离散近红外波段、红光波段、NDVI值落在拟合中稻、晚稻近红外波段、红光波段、NDVI时间序列曲线两侧的敏感性区域的比例,该区域也可以视为水稻作物识别特征的目标特征区域,只有达到一定的比例才能视为某类水稻作物。在此情形下,需要综合3种情况进行集中投票决定其最终分类结果。研究表明：该方法可以在多云雾地区对中稻和晚稻精确识别,中稻和晚稻用户精度可达95.97%和95.95%,总体精度为95.76%,kappa系数为0.9335。实验结果表明了NIR、R、NDVI时间序列曲线拟合的有效性,以及拟合曲线目标特征区域设置的合理性。

关键词: 水稻, 遥感, 光谱模拟, 分类, 时间序列

Abstract:

Food security is an important guarantee for the stable development of our country and the area of planting grain is the basis of food security, so the estimation of the area of planting grain is important. Remote sensing technology is an important method of estimating crop grain area at present. The classification accuracy is affected by cloud and mist, which cannot be avoided. To solve this problem, this study presented a method for recognizing rice based on GF-1 time-series image. With long time-series of GF-1 images, three indices of middle-season rice and late-season rice, namely near infrared band reflectance (NIR), red (R) band reflectance and the normalized difference vegetation index (NDVI) characteristics are extracted. Spectrum and the characteristic curve of vegetation index time-series are fitted. We analyzed the ratios of values of discrete near infrared band, red light band and NDVI of images of multiple temporal phases falling on both sides of the sensitive area of the fitting NIR, R and NDVI time-series curve of middle-season rice and late-season rice. This area can also be seen as the target area of rice identification features and only those reaching a certain proportion can be identified as certain type of rice. Under this condition, three kinds of situation should be considered comprehensively and voted to decide final classification results. The means of samples are used to fit the curve for each image. The outliers are eliminated from the ground samples in advance. Statistical analysis of ground samples defined target characteristics. The result indicated that: (1) Using polynomial fitting method based on least square principle to fit NIR, R, NDVI time series characteristic curve, fitting effect is better when fitting degree is 3 and it can satisfy the need of subsequent classification. (2) Different setting proportions led to different classification accuracy, and the overall accuracy is 95.76%, the user accuracy of middle-season rice and late-season is 95.97% and 95.95% when the setting proportion is not less than 50%. (3) The method proposed in this study could solve the problem of the combination of complex phases, and significantly weaken the influence of cloud and fog on crop classification, especially in South China.

Key words: rice, remote sensing, spectrum simulation, classification, time series

宋盼盼, 杜鑫, 吴良才, 王红岩, 李强子, 王娜. 基于光谱时间序列拟合的中国南方水稻遥感识别方法研究[J]. 地球信息科学学报, 2017, 19(1): 117-124.DOI:10.3724/SP.J.1047.2017.00117

SONG Panpan,DU Xin,WU Liangcai,WANG Hongyan,LI Qiangzi,WANG Na. Research on the Method of Rice remote sensing Identification Based on SpectralTime-series Fitting in Southern China[J]. Journal of Geo-information Science, 2017, 19(1): 117-124.DOI:10.3724/SP.J.1047.2017.00117

图/表 7

表1

表2

图1

表3

表4

图2

图3

参考文献 25

[1]	Liu J, Liu, M, Tian H, et al. Spatial and temporal patterns of China's cropland during 1990-2000: An analysis based on Landsat TM data[J]. Remote Sensing of Environment, 2005,98(4):442-456. doi: 10.1016/j.rse.2005.08.012
[2]	Chen L.Uncertainties in rice yield estimation using remote sensing data[D]. Huangzhou: Zhejiang University, 2007.
[3]	郑长春,王秀珍,黄敬峰.多时相MODIS影像的浙江省水稻种植面积信息提取方法研究[J].浙江大学学报(农业与生命科学版),2009,35(1):98-104. doi: 10.3785/j.issn.1008-9209.2009.01.015
	[ Zheng C C, Wang X Z, Huang J F.Mapping paddy rice planting area in Zh-ejiang Province using multi-temporal MODIS images[J]. Journal of Zhejiang University (Agric & Life Sci), 2009,35(1):98-104. ] doi: 10.3785/j.issn.1008-9209.2009.01.015
[4]	张焕雪. 湖南省水稻种植面积估算及精度影响研究[D].北京:中国科学院大学,2014.
	[ Zhang H X.Rice acreage estimation and accuracy influences analysis in Hunan province[D]. Beijing: University of Chinese Academy of Sciences, 2014. ]
[5]	吴炳方. 中国农情遥感速报系统[J].遥感学报,2004,8(6):481-497. doi: 10.11834/jrs.20040601
	[ Wu B F.China Crop Watch System with Rem-ote Sensing[J]. Journal of Remote Sensing, 2004,8(6):481-497. ] doi: 10.11834/jrs.20040601
[6]	贾坤,李强子.农作物遥感分类特征变量选择研究现状与展望[J].资源科学,2013,35(12):2507-2516.
	[ Jia K, Li Q Z.Review of Features Selection in Crop Classification Using Remote Sensing Data[J]. Resources Science, 2013,35(12):2507-2516. ]
[7]	江东,王乃斌,杨小唤,等.NDVI曲线与农作物长势的时序互动规律[J].生态学报,2002,22(2):247-252. doi: 10.3321/j.issn:1000-0933.2002.02.015
	[ Jiang D, Wang N B, Yang X H, et al.Principles of the Interaction Between ND YI Profile and the Growing Situation of Crops[J]. Acta Ecologica Sinica, 2002,22(2):247-252. ] doi: 10.3321/j.issn:1000-0933.2002.02.015
[8]	索玉霞,王正兴.基于决策树和MODIS植被指数时间序列的中亚土地覆盖分类[J].世界地理研究,2008,17(3):126-130. doi: 10.3969/j.issn.1004-9479.2008.03.017
	[ Suo Y X, Wang Z X. Land cover classification of middle Asia based on decision tree and MODIS vegetation index time serials[J]. World Regional Studies, 2008,17(3)126-130. ] doi: 10.3969/j.issn.1004-9479.2008.03.017
[9]	杨小唤,张香平,江东.基于MODIS时序NDVI特征值提取多作物播种面积的方法[J].资源科学,2004,26(6):17-22. doi: 10.3321/j.issn:1007-7588.2004.06.003
	[ Yang X H, Zhang X P, Jiang D.Extraction of multi-chop planting areas from MODIS data[J]. Resources Science, 2004,26(6):17-22. ] doi: 10.3321/j.issn:1007-7588.2004.06.003
[10]	刘佳,王利民,杨福刚,等.基于HJ时间序列数据的农作物种植面积估算[J].农业工程学报,2015,31(3)199-206. doi: 10.3969/j.issn.1002-6819.2015.03.026
	Liu J ,Wang L M ,Yang F G, et al.Remote sensing estimation of crop planting area based on HJ time-series images[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(3)199-206. ] doi: 10.3969/j.issn.1002-6819.2015.03.026
[11]	王琳,景元书,杨沈斌.基于多时相遥感数据提取水稻种植面积的研究[J].中国农业资源与区划,2013,34(2):21-26. doi: 10.7621/cjarrp.1005-9121.20130204
	[ Wang L, Jing Y S,Yang S B.Study on extraction of rice cropping area using multi-temporal remote sensing data[J]. Chinese Journal of Agricultural Resources and Regional Planning, 2013,34(2):21-26. ] doi: 10.7621/cjarrp.1005-9121.20130204
[12]	杨闫君,占玉林,田庆久,等.基于GF-1/WFVNDVI时间序列数据的作物分类[J].农业工程学报,2015,31(24):155-161. doi: 10.11975/j.issn.1002-6819.2015.24.024
	[Yang Y Q, Zhan Y L, Tian Q J, et al.Crop classification based on GF-1/WFV NDVI time-series[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(24):155-161. ] doi: 10.11975/j.issn.1002-6819.2015.24.024
[13]	李鑫川,徐新刚,王纪华,等.基于时间序列环境卫星影像的作物分类识别[J].农业工程学报,2013,29(2):169-176,298. doi: 10.3969/j.issn.1002-6819.2013.02.024
	[ Li X C, Xu X G, Wang J H, et al.Crop classification recognition based on time-series images from HJ satellite[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013,29(2):169-176,298. ] doi: 10.3969/j.issn.1002-6819.2013.02.024
[14]	张焕雪,曹新,李强子,等.基于多时相环境星NDVI时间序列的农作物分类研究[J].遥感技术与应用,2015,30(2):304-311. doi: 10.11873/j.issn.1004-0323.2015.2.0304
	[ Zhang H X, Cao X, Li Q Z, et al.Research on crop identification using multi-temporal NDVI HJ images[J]. Remote Sensing Technology and Application, 2015,30(2):304-311. ] doi: 10.11873/j.issn.1004-0323.2015.2.0304
[15]	宋晓宇,刘良云,李存军,等.基于单景遥感影像的去云处理研究[J].光学技术,2006,32(2):299-303. doi: 10.3321/j.issn:1002-1582.2006.02.043
	[ Song X Y, Liu L Y, Li C J, et al.Cloud removing based on single remote sensing image[J]. Optical Technique, 2006,32(2):299-303. ] doi: 10.3321/j.issn:1002-1582.2006.02.043
[16]	马建文,顾行发,冯春,等.CBERS-02卫星图像薄云的去除方法研究[J].中国科学E辑:信息科学,2005(S1):89-96. doi: 10.3321/j.issn:1006-9275.2005.z1.007
	[ Ma J W, Gu X F, Feng C, et al.Research on methods for GPS receiver clock offset prediction[J]. Science in China Series E: Information Sciences, 2005,S1:89-96. ] doi: 10.3321/j.issn:1006-9275.2005.z1.007
[17]	梁守真,施平,邢前国.MODISNDVI时间序列数据的去云算法比较[J].国土资源遥感,2011(1)33-36. doi: 10.3724/SP.J.1011.2011.00403
	[ Liang S Z, Shi P, Xing Q G.A Caparison between the algorithms for removing cloud pixel from MODISNDVI time series data[J]. Remote Sensing for Land & Resources, 2011:133-36. ] doi: 10.3724/SP.J.1011.2011.00403
[18]	刘国栋,邬明权,牛铮,等.基于GF-1卫星数据的农作物种植面积遥感抽样调查方法[J].农业工程学报,2015,31(5):160-166. doi: 10.3969/j.issn.1002-6819.2015.05.023
	[ Liu G D, Wu M Q, Niu Z, et al.Investigation method for crop area using remote sensing sampling based on GF-1Satellite data[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2015,31(5):160-166. ] doi: 10.3969/j.issn.1002-6819.2015.05.023
[19]	Vermote E F, Tanre D, Deuze J L, et al.Second simulation of the satellite signal in the solar spectrum, 6S: An ove-rview[J]. IEEE Transactions on Geoscience and Remote Sensing, 1997,35(3):675-686. doi: 10.1109/36.581987
[20]	Rouse J W, Haas R H, Schell J A, et al.Monitoring vegetation systems in the Great Plains with ERTS[C]//Stanley C F. Proceedings of third earth resources technology satellite symposium, Washington: NASA Special Publication, 1974:310-317.
[21]	张威,潘剑君,李勇,等.基于冠层光谱特征的冬小麦产量估算研究[J].土壤通报,2015,46(1):169-176.
	[ Zhan g W, Pan J J, Li Y, et al. Research on Estimation of grain yield of winter wheat based on canopy spectrum characteristics[J].Chinese Journal of Soil Science, 2015,46(1):169-176. ]
[22]	张敏,袁辉.拉依达(Pau Ta)准则与异常值剔除[J].郑州工业大学学报,1997,18(1):87-91.
	[ Zhang M, Yuan H.The Pau Ta criterion and rejecting the abnormal value[J]. Journal of Zhengzhou University of Technology, 1997,18(1):87-91. ]
[23]	陈岚峰,杨静瑜,崔崧,等.基于MATLAB的最小二乘曲线拟合仿真研究[J].沈阳师范大学学报(自然科学版),2014,32(1):75-79. doi: 10.3969/j.issn.1673-5862.2014.01.016
	[ Chen L F, Yang J Y, Cui S, et al.MATLAB simulation of curve fitting based on least-squares[J]. Journal of Shenyang Normal University (Natural Science Edition), 2014,32(1):75-79. ] doi: 10.3969/j.issn.1673-5862.2014.01.016
[24]	陈光,任志良,孙海柱.最小二乘曲线拟合及Matlab实现[J].兵工自动化,2005,24(3):107-108. doi: 10.3969/j.issn.1006-1576.2005.03.051
	[ Chen G, Ren Z L, Sun H Z.Curve fitting in least-square method and its realization with Matlab[J]. Ordnance Industry Automati on, 2005,24(3):107-108. ] doi: 10.3969/j.issn.1006-1576.2005.03.051
[25]	萧耐园. 周期律在公历纪日中的快速显示及其应用[J].南京大学学报(自然科学版),1995,31(4):539-547.
	[ Xiao N Y.A rapid reval of periodicities on measure of the civil calendars` dates and its aplications[J]. Journal of Nan jing Unversity (Natural Sciences), 1995,31(4):539-547. ]

	月份
	6月	7月	8月	9月	10月	11月
旬	上中下	上中下	上中下	上中下	上中下	上中下
中稻	插秧	分蘖	拔节	抽穗灌浆	成熟
晚稻	插秧	分蘖	拔节	抽穗	灌浆成熟

影像时相编号	影像获取时间	儒略日	传感器	影像质量
N1	2014-06-14	194	WFV2	少量云雾
N2	2014-07-21	231	WFV2	少量云团
N3	2014-07-30	240	WFV4	无云雾
N4	2014-08-06	246	WFV1	多云团
N5	2014-09-04	274	WFV2	多云团
N6	2014-09-21	291	WFV4	多云团
N7	2014-09-28	298	WFV1	无云雾
N8	2014-10-07	307	WFV3	少量云团
N9	2014-10-15	315	WFV2	无云雾
N10	2014-10-24	324	WFV4	无云雾
N11	2014-11-04	334	WFV1	无云雾

比例	总体精度/%	Kappa系数
不少于40%	89.13	0.8637
不少于50%	95.76	0.9335
不少于60%	80.85	0.7812

类别	中稻	晚稻	其他植被	总计	用户精度/%
中稻	2978	76	45	3103	95.97
晚稻	80	3154	57	3287	95.95
其他植被	36	41	1439	1516	94.92
总计	3090	3275	1541
生产精度/%	96.38	96.31	93.39
总体精度/%	95.76
Kappa系数	0.9335

基于光谱时间序列拟合的中国南方水稻遥感识别方法研究

Research on the Method of Rice remote sensing Identification Based on SpectralTime-series Fitting in Southern China

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 25

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	罗秋雨, 乐阳, 谷岩岩. 城市地铁出行知识图谱嵌入表达的超参数选择[J]. 地球信息科学学报, 2023, 25(6): 1164-1175.
[2]	杨颖频, 吴志峰, 黄启厅, 骆剑承, 吴田军, 董文, 胡晓东, 肖文菊. 协同遥感与统计数据的粤西甘蔗种植分布提取及时空分析[J]. 地球信息科学学报, 2023, 25(5): 1012-1026.
[3]	刘潇, 刘智, 林雨准, 王淑香, 左溪冰. 面向遥感影像场景分类的类中心知识蒸馏方法[J]. 地球信息科学学报, 2023, 25(5): 1050-1063.
[4]	陈科, 管海燕, 雷相达, 曹爽. 基于特征增强核点卷积网络的多光谱LiDAR点云分类方法[J]. 地球信息科学学报, 2023, 25(5): 1075-1087.
[5]	史雪威, 陈绪慧, 蔡明勇, 张新胜, 申振, 邰文飞, 申文明, 李静, 肖桐. 宁夏全区及生态保护红线生态系统服务价值变化评估[J]. 地球信息科学学报, 2023, 25(5): 999-1011.
[6]	封雅静, 翟亮, 桑会勇, 成思远. 基于精细单元碳收支核算及变化分类方法[J]. 地球信息科学学报, 2023, 25(3): 468-478.
[7]	衡雪彪, 许捍卫, 唐璐, 汤恒, 许怡蕾. 基于改进全卷积神经网络模型的土地覆盖分类方法研究[J]. 地球信息科学学报, 2023, 25(3): 495-509.
[8]	巫磊, 吴文挺. GEE平台下结合滤波算法和植被物候特征的互花米草遥感提取最优时间窗口确定[J]. 地球信息科学学报, 2023, 25(3): 606-624.
[9]	高鹏飞, 曹雪峰, 李科, 游雄. 融合多元稀疏特征与阶层深度特征的遥感影像目标检测[J]. 地球信息科学学报, 2023, 25(3): 638-653.
[10]	秦肖伟, 程博, 杨志平, 李林, 董文, 张新, 杨树文, 靳宗义, 薛庆. 基于时序遥感影像的西南山区地块尺度作物类型识别[J]. 地球信息科学学报, 2023, 25(3): 654-668.
[11]	陈凯, 雷少华, 代文, 王春, 刘爱利, 李敏. 基于开源数据和条件生成对抗网络的地形重建方法[J]. 地球信息科学学报, 2023, 25(2): 252-264.
[12]	饶子昱, 卢俊, 郭海涛, 余东行, 侯青峰. 利用视角转换的跨视角影像匹配方法[J]. 地球信息科学学报, 2023, 25(2): 368-379.
[13]	王龙号, 蓝朝桢, 姚富山, 侯慧太, 武蓓蓓. 多源遥感影像深度特征融合匹配算法[J]. 地球信息科学学报, 2023, 25(2): 380-395.
[14]	黎煜昭, 刘启亮, 邓敏, 徐锐, 王茂洋, 杨海南. 基于物理约束GRU神经网络的河流水质预测模型[J]. 地球信息科学学报, 2023, 25(1): 102-114.
[15]	甘聪聪, 邱炳文, 张建阳, 姚铖鑫, 叶智燕, 黄姮, 黄莹泽, 彭玉凤, 林艺真, 林多多, 苏中豪. 基于Sentinel-1/2动态耦合移栽期特征的水稻种植模式识别[J]. 地球信息科学学报, 2023, 25(1): 153-162.