关键生育期冬小麦和油菜遥感分类方法

doi:10.12082/dqxxkx.2019.180421

地球信息科学学报 ›› 2019, Vol. 21 ›› Issue (7): 1121-1131.doi: 10.12082/dqxxkx.2019.180421

关键生育期冬小麦和油菜遥感分类方法

王林江^1,²(), 吴炳方^1,^2,^*(), 张淼¹, 邢强¹

1. 中国科学院遥感与数字地球研究所遥感科学国家重点实验室,北京100101
2. 中国科学院大学,北京 100049

收稿日期:2018-08-29 修回日期:2019-03-26 出版日期:2019-07-25 发布日期:2019-07-25
通讯作者: 吴炳方 E-mail:wanglj@radi.ac.cn;wubf@radi.ac.cn
作者简介:
作者简介：王林江（1995-）,男,山西太原人,博士生,主要从事农业和水资源遥感的研究。E-mail: wanglj@radi.ac.cn
基金资助:
国家重点研发计划项目（2016YFD0300608）;中国科学院科技服务网络计划（STS计划）项目（KFJ-STS-ZDTP-009）;国家自然科学基金项目（41561144013、41701496、41601463、41701403）

Winter Wheat and Rapeseed Classification during Key Growth Period by Integrating Multi-Source Remote Sensing Data

Linjiang WANG^1,²(), Bingfang WU^1,^2,^*(), Miao ZHANG¹, Qiang XING¹

1. State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2018-08-29 Revised:2019-03-26 Online:2019-07-25 Published:2019-07-25
Contact: Bingfang WU E-mail:wanglj@radi.ac.cn;wubf@radi.ac.cn
Supported by:
National Key Research and Development Program of China, No.2016YFD0300608;Science and Technology Service Network Initiative, No.KFJ-STS-ZDTP-009;National Natural Science Foundation of China, No.41561144013, 41701496, 41601463, 41701403

摘要/Abstract

摘要：

农作物空间分布的遥感识别是地理学、生态学和农学等多学科研究的前沿和热点,多源遥感数据在其中发挥着重要的作用。本研究结合冬小麦和油菜的种植及生长特点,以安徽省合肥市为研究区域,利用ZY-3、Sentinel-2和GF-1等多源遥感影像数据,以高程、坡度等数据为辅助信息,结合以多尺度分割、最邻近法和阈值法等为主要步骤的面向对象的分类方法,提取研究区合肥市冬小麦和油菜种植的空间分布信息。结合来自于GVG农情采样系统和Google Earth高分辨率影像上获得的地面验证数据进行分类精度验证,计算得到分类结果的混淆矩阵,并根据混淆矩阵数据计算出分类的总体精度为94.43%,Kappa系数为0.914。结果表明,本研究提出的方法能够有效地区分在冬小麦和油菜的混种区域里两种作物种植区域的空间分布,且这种多种策略相结合的分类方法体系,能够适用于其它区域甚至是更加大尺度上的作物分类。

关键词: 关键生育期, 多源遥感数据, 冬小麦, 油菜, 面向对象分类, 合肥市

Abstract:

As the cutting-edge technology of modern information technology, remote sensing has the advantages of large coverage, short detection period, strong current situation, and low cost, which makes it possible to quickly and accurately extract large-scale crop planting information. Accurate crop type identification and spatial distribution information can provide basic and necessary information for subsequent crop monitoring applications. Identification of crop spatial distribution by remote sensing is the frontier and a hotspot of multidisciplinary research in geography, ecology, and agronomy. Multi-source remote sensing data plays an important role. Combining the characteristics of winter wheat and rapeseed during their planting and growing stages, this study took Hefei City in Anhui Province as the study area, and used multi-source remote sensing imagery such as ZY-3, Sentinel-2, and GF-1, with elevation and slope data as auxiliary information. Utilizing the object-oriented classification method with multi-scale segmentation, nearest neighbor method, and threshold method as the main steps, the spatial distribution information of winter wheat and rapeseed planting in Hefei City was extracted. Ground truth data from the GVG agricultural sampling system and Google Earth high-resolution imagery were combined to verify the accuracy of the classification results. By confusion matrix analysis, the overall accuracy and the kappa Coefficient were calculated, the values of which were 94.43% and 0.914, respectively. The results show that, to a large extent, the proposed method can effectively distinguish the planting areas of winter wheat and rapeseed in the mixed planting regions and the combination of those various strategies can be applied to the crop classification in other regions with similar characteristics and at even larger scales. Future research can explore the feasibility of using multi-source remote sensing data to map winter wheat and rapeseed for remote sensing monitoring, and can establish a suitable technical system.

Key words: Key growth period, multi-source remote sensing data, winter wheat, rapeseed, object-oriented classification, Hefei

王林江, 吴炳方, 张淼, 邢强. 关键生育期冬小麦和油菜遥感分类方法[J]. 地球信息科学学报, 2019, 21(7): 1121-1131.DOI:10.12082/dqxxkx.2019.180421

Linjiang WANG, Bingfang WU, Miao ZHANG, Qiang XING. Winter Wheat and Rapeseed Classification during Key Growth Period by Integrating Multi-Source Remote Sensing Data[J]. Journal of Geo-information Science, 2019, 21(7): 1121-1131.DOI:10.12082/dqxxkx.2019.180421

图/表 13

图1

表1

表2

表3

图2

图3

图4

图5

图6

图7

图8

图9

表4

参考文献 33

[1]	宋茜,周清波,吴文斌,等.农作物遥感识别中的多源数据融合研究进展[J].中国农业科学,2015,48(6):1122-1135.
	[ Song Q, Zhou Q B, Wu W B, et al.Recent progresses in research of integrating multi-source remote sensing data for crop mapping[J]. Scientia Agricultura Sinica, 2015,48(6):1122-1135. ]
[2]	Ozdogan M.The spatial distribution of crop types from MODIS data: Temporal unmixing using independent component analysis[J]. Remote Sensing of Environment, 2010,114(6):1190-1204. doi: 10.1016/j.rse.2010.01.006
[3]	唐华俊,吴文斌,杨鹏,等.农作物空间格局遥感监测研究进展[J].中国农业科学,2010,43(14):2879-2888.
	[ Tang H J, Wu W B, Yang P, et al.Recent progresses in monitoring crop spatial patterns by using remote sensing technologies[J]. Scientia Agricultura Sinica, 2010,43(14):2879-2888. ]
[4]	Brown J C, Kastens J H, Coutinho A C, et al. Classifying multiyear agricultural land use data from Mato Grosso using time-series MODIS vegetation index data[J]. Remote Sensing of Environment, 2013,130(4)3:9-50.
[5]	Zhang X, Zhang M, Zheng Y, et al.Crop mapping using PROBA-V time series data at the Yucheng and Hongxing Farm in China[J]. Remote Sensing, 2016,8(11):915. doi: 10.3390/rs8110915
[6]	陈水森,柳钦火,陈良富,等.粮食作物播种面积遥感监测研究进展[J].农业工程学报,2005,21(6):166-171.
	[ Chen S S, Liu Q H, Chen L F, et al.Review of research advances in remote sensing monitoring of grain crop area[J]. Transactions of the Chinese Society of Agricultural Engineering, 2005,21(6):166-171. ]
[7]	Sun H, Xu A, Lin H, et al.Winter wheat mapping using temporal signatures of MODIS vegetation index data[J]. International Journal of Remote Sensing, 2012,33(16):5026-5042. doi: 10.1080/01431161.2012.657366
[8]	Brown M E.Remote sensing technology and land use analysis in food security assessment[J]. Journal of Land Use Science, 2016,11(6):623-641. doi: 10.1080/1747423X.2016.1195455
[9]	Singha M, Wu B, Zhang M.Object-based paddy rice mapping using HJ-1A/B data and temporal features extracted from time series MODIS NDVI data[J]. Sensors, 2016,17(1):10. doi: 10.3390/s17010010
[10]	Zheng Y, Zhang M, Zhang X, et al.Mapping winter wheat biomass and yield using time series data blended from PROBA-V 100- and 300-m S1 products[J]. Remote Sensing, 2016,8(10):824. doi: 10.3390/rs8100824
[11]	王九中,田海峰,邬明权等.河南省冬小麦快速遥感制图[J].地球信息科学学报,2017,19(6):846-853.
	[ Wang J Z, Tian H F, Wu M Q, et al.Rapid mapping of winter wheat in Henan province[J]. Journal of Geo-information Science, 2017,19(6):846-853. ]
[12]	Kun Jia, Qiangzi Li, Yichen Tian, et al.Crop classification using multi-configuration SAR data in the North China Plain[J]. International Journal of Remote Sensing, 2012,33(1):170-183. doi: 10.1080/01431161.2011.587844
[13]	许文波,张国平,范锦龙,等.利用MODIS遥感数据监测冬小麦种植面积[J].农业工程学报,2007,23(12):144-149.
	[ Xu W B, Zhang G P, Fan J L, et al.Monitoring winter wheat planting area using MODIS remote sensing data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2007,23(12):144-149. ]
[14]	王启田,林祥国,王志军,等.利用面向对象分类方法提取冬小麦种植面积的研究[J].测绘科学,2008,33(2):143-146.
	[ Wang Q T, Lin X G, Wang Z J, et al.Extraction of winter wheat planting area using object-oriented classification method[J]. Journal of Surveying and Mapping, 2008,33(2):143-146. ]
[15]	Pan Y, Li L, Zhang J, et al.Winter wheat area estimation from MODIS-EVI time series data using the Crop Proportion Phenology Index[J]. Remote Sensing of Environment, 2012,119(3):232-242. doi: 10.1016/j.rse.2011.10.011
[16]	佘宝,黄敬峰,石晶晶,等.基于红边位置变化特征的油菜种植区域提取[J].农业工程学报,2013,29(15):145-152.
	[ She B, Huang J F, Shi J J, et al.Extracting oilseed rape growing regions based on variation characteristics of red edge position[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013,29(15):145-152. ]
[17]	王立辉,黄进良,孙俊英.基于线性光谱混合模型的油菜种植面积遥感监测方法研究[J].遥感信息,2010(3):55-59.
	[ Wang L H, Huang J L, Sun J Y.Study on remote sensing monitoring of rape acreage based on Linear Spectral Mixture model[J]. Remote Sensing Information, 2010(3):55-59. ]
[18]	Fieuzal R, Baup F, Maraissicre C.Monitoring wheat and rapeseed by using synchronous optical and radar satellite data—from temporal signatures to crop parameters estimation[J]. Advances in Remote Sensing, 2013,2(2):162-180. doi: 10.4236/ars.2013.22020
[19]	姬忠林,张月平,李乔玄,等.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.
	[ Ji Z L, Zhang Y P, Li Q X, et al.Planting information extraction of winter wheat and rape based on GF-1 image[J]. Remote Sensing Technology and Application, 2017,32(4):760-765. ]
[20]	梁益同,万君.基于HJ-1A/B-CCD影像的湖北省冬小麦和油菜分布信息的提取方法[J].中国农业气象,2012,33(4):573-578. doi: 10.3969/j.issn.1000-6362.2012.04.015
	[ Liang Y T, Wan J.Application of HJ-1A/B-CCD images in extracting the distribution of winter wheat and rape in Hubei province[J]. Chinese Journal of Agro-meteorology, 2012,33(4):573-578. ] doi: 10.3969/j.issn.1000-6362.2012.04.015
[21]	鲍恩财,田争光,刘伟伟等.主要农作物秸秆资源调查及能源化利用评价——以安徽省为例[J].中国农学通报,2014,30(29):222-228.
	[ Bao E C, Tian Z G, Liu W W, et al.Main crop straw resources investigation and energy utilization evaluation—taking Anhui province as an example[J]. Chinese Agricultural Science Bulletin, 2014,30(29):222-228. ]
[22]	申科.主要作物物候历[EB/OL]., 2016-2-16.
	[ Shen K, Major crop phenology[EB/OL]. , 2016-2-16. ]
[23]	中国资源卫星应用中心.高分一号[EB/OL]., 2014-10-15.
	[ CRESDA, Gaofen-1 satellite[EB/OL]. , 2014-10-15. ]
[24]	中国资源卫星应用中心.资源三号[EB/OL]., 2014-10-15.
	[ CRESDA. Ziyuan-3 satellite[EB/OL]. , 2014-10-15. ]
[25]	Suhet.Sentinel-2 User Handbook[EB/OL].,2013-9-1.
[26]	吴炳方,田亦陈,李强子. GVG农情采样系统及其应用[J].遥感学报,2004,8(6):570-580. doi: 10.11834/jrs.20040606
	[ Wu B F, Tian Y C, Li Q Z.GVG, a crop type proportion sampling instrument[J]. Journal of Remote Sensing, 2004,8(6):570-580. ] doi: 10.11834/jrs.20040606
[27]	Witharana C, Civco D L.Optimizing multi-resolution segmentation scale using empirical methods: Exploring the sensitivity of the supervised discrepancy measure Euclidean distance 2 (ED2)[J]. Isprs Journal of Photogrammetry & Remote Sensing, 2014,87(1):108-121.
[28]	佃袁勇,方圣辉,姚崇怀.多尺度分割的高分辨率遥感影像变化检测[J].遥感学报,2016,20(1):129-137.
	[ Yan Y Y, Fang S H, Yao C H.Change detection for high-resolution images using multilevel segment method[J]. Journal of Remote Sensing, 2016,20(1):129-137. ]
[29]	吴剑. 基于面向对象技术的遥感震害信息提取与评价方法研究[D].武汉:武汉大学,2010
	[ Wu J.The research of earthquake information extraction and assessment based on object-oriented technology with remotely-sensed data[D]. Wuhan: Wuhan University, 2010. ]
[30]	杨飞,刘丽峰,王学成.基于面向对象方法和SPOT5的丘陵山区林地分类研究[J].林业资源管理,2014(5):92-99.
	[ Yang F, Liu L F, Wang X C.Study on forest classification based on object-oriented method and SPOT5 images in hilly mountain area[J]. Forest Resources Management, 2014(5):92-99. ]
[31]	胡琰. 基于OBIA方法的土地利用遥感变化检测研究[D].西安:长安大学,2017.
	[ Hu W.Study on land use remote sensing detection based on OBIA method[D]. Xi'an: Chang'an University, 2017. ]
[32]	雷光斌,李爱农,边金虎,等.基于阈值法的山区森林常绿、落叶特征遥感自动识别方法—以贡嘎山地区为例[J].生态学报,2014,34(24):7210-7221. doi: 10.5846/stxb201310112440
	[ Lei G B, Li A N, Bian J H, et al.A practical method for automatically identifying the evergreen and deciduous characteristic of forests at mountainous areas: A case study in Mt. Gongga Region[J].Acta Ecologica Sinica, 2014,34(24):7210-7221. ] doi: 10.5846/stxb201310112440
[33]	Yi L, Zhang G.Object-oriented remote sensing imagery classification accuracy assessment based on confusion matrix[C]// International Conference on Geoinformatics. IEEE, 2012:1-8.

	波段号	波长范围/μm	空间分辨率/m	幅宽/km	轨道高度/km	重放周期/d
ZY3-02	1	0.450~0.520	5.8	51	505	3
	2	0.520~0.590
	3	0.630~0.690
	4	0.770~0.890
Sentinel2-MSI	2	0.430~0.550	10	290	786	10
	3	0.515~0.605
	4	0.623~0.702
	8	0.765~0.920
GF1-WFV	1	0.450~0.520	16	800	645	2
	2	0.520~0.590
	3	0.630~0.690
	4	0.770~0.890

	获取时间(数量)
ZY3-02	2月16日(2景)、2月26日(1景)、3月8日(2景)、4月16日(2景)
Sentinel2-MSI	3月26日(5景)、4月2日(3景)、4月15日(2景)、4月22日(1景)
GF1-WFV	4月18日(1景)

地面类型	像元数/个			使用者精度/%
地面类型	冬小麦	油菜	其他植被	使用者精度/%
冬小麦	179	6	2	95.72
油菜	13	300	3	95.72
其他植被	7	9	199	92.56
生产者精度/%	89.95	95.24	97.55
总体精度/%	94.43
kappa系数	0.914

关键生育期冬小麦和油菜遥感分类方法

Winter Wheat and Rapeseed Classification during Key Growth Period by Integrating Multi-Source Remote Sensing Data

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 33

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	王维佳, 王汶, 杨熙, 赵彦云. 基于MODIS GPP产品的冬小麦保险费率厘定方法研究[J]. 地球信息科学学报, 2020, 22(7): 1578-1587.
[2]	张志慧, 刘雯, 李笑含, 朱靖轩, 张洪涛, 杨东, 徐超昊, 徐宪立. 基于无人机航摄影像的喀斯特地区裸岩信息提取及景观格局分析[J]. 地球信息科学学报, 2020, 22(12): 2436-2444.
[3]	谭深, 吴炳方, 张鑫. 基于Google Earth Engine与多源遥感数据的海南水稻分类研究[J]. 地球信息科学学报, 2019, 21(6): 937-947.
[4]	李中元, 吴炳方, 张淼, 邢强, 李名勇, 闫娜娜. 利用物候差异与面向对象决策树提取油菜种植面积[J]. 地球信息科学学报, 2019, 21(5): 720-730.
[5]	肖池伟,饶滴滴,刘怡媛,封志明,李鹏. 地缘经济合作背景下的中国磨憨-老挝磨丁口岸地区建设用地扩张[J]. 地球信息科学学报, 2019, 21(10): 1576-1585.
[6]	冯素云, 张凯选, 鹿琳琳. “海上丝绸之路”超大城市环境变化遥感分析[J]. 地球信息科学学报, 2018, 20(5): 602-612.
[7]	宋晓阳, 黄耀欢, 董东林, 张飞. 融合数字表面模型的无人机遥感影像城市土地利用分类[J]. 地球信息科学学报, 2018, 20(5): 703-711.
[8]	王九中, 田海峰, 邬明权, 王力, 王长耀. 河南省冬小麦快速遥感制图[J]. 地球信息科学学报, 2017, 19(6): 846-853.
[9]	陈天博, 胡卓玮, 魏铼, 胡顺强. 无人机遥感数据处理与滑坡信息提取[J]. 地球信息科学学报, 2017, 19(5): 692-701.
[10]	李治, 杨晓梅, 孟樊, 陈曦, 杨丰硕. 城市建成区多源遥感协同提取方法研究[J]. 地球信息科学学报, 2017, 19(11): 1522-1529.
[11]	关舒婧, 韩鹏鹏, 王月如, 韩宇, 易琳, 周廷刚, 陈劲松. 华南地区典型种植园地遥感分类研究[J]. 地球信息科学学报, 2017, 19(11): 1538-1546.
[12]	郭昱杉, 刘庆生, 刘高焕, 黄翀. 基于标记控制分水岭分割方法的高分辨率遥感影像单木树冠提取[J]. 地球信息科学学报, 2016, 18(9): 1259-1266.
[13]	唐志光, 李弘毅, 王建, 梁继, 李朝奎, 车涛, 王欣. 基于多源数据的青藏高原雪深重建[J]. 地球信息科学学报, 2016, 18(7): 941-950.
[14]	方朝阳, 邬浩, 陶长华, 高丹, 周华. 鄱阳湖南矶湿地景观信息高分辨率遥感提取[J]. 地球信息科学学报, 2016, 18(6): 847-856.
[15]	吴田军, 骆剑承, 沈占锋, 夏列钢, 徐楠. 高分辨率遥感土地覆盖分类技术的应用研究——以重庆市黔江贫困区为例[J]. 地球信息科学学报, 2016, 18(3): 353-361.