基于多时相Landsat 8 OLI影像的农作物遥感分类研究
|
摘要
时序遥感数据及地物细微光谱特征对于提取作物分布有重要作用,基于此,利用多时相Landsat 8 OLI影像,结合光谱角填图和决策树分类提取大同市新荣区东部地区主要农作物分布情况,并与最大似然法提取的分布结果进行对比。研究发现:①研究区内春玉米、谷物、大豆和马铃薯种植面积依次减小并呈镶嵌式分布;②结合光谱角填图与决策树分类总体精度为85.34%,Kappa系数为0.76,与最大似然法结果相比,总体精度提高22.51%,Kappa系数增加0.31,分类结果与实际作物分布具有更好的一致性;③利用时序遥感影像进行作物分类的精度明显高于单时相遥感影像的分类精度,且从光谱角差异的角度分析时序数据可有效削弱中高分辨率影像物谱不一致现象的影响。研究结果验证了多时相遥感影像对农作物分类研究的积极作用,并发展了光谱角填图法结合决策树分类在中高分辨率遥感影像中进行农作物分类的用法,具有一定的应用前景。
It is crucial for agricultural production to know crop planting situation.Temporal remote sensing images and subtle spectral characteristics of ground features play an important role in extracting crops distribution.At this point,multi-temporal Landsat 8 OLI images were used to extracting the distribution of main crops in the east of Xinrong district of Datong city by using Spectral Angle Mapper(SAM) combined with the decision tree classification,and the extracting result was compared with the result that maximum likelihood extracted.The results show that:① The planting area of spring corn,grain,soybean and potato is decreased and mosaic distribution in order.② The overall accuracy obtained by SAM combined with the decision tree classification is 85.34% and the Kappa coefficient is 0.76,which is outperformed the results of maximum likelihood with the increase of 22.51% and 0.31,respectively,the classification results was more consistent with the actual distribution of main crops.③ The classification accuracy of main crops used the multi-temporal remote sensing images was obviously higher than that of single-temporal image,and the difference between ground features and spectra in middle or high resolution images can effectively weaken by analyzing multi-temporal data from the perspective of difference of spectral angle.The results not only confirmed the positive effect of multi-temporal remote sensing images on crops classification,but also developed the SAM combined with decision tree classification in crops classification of medium-high resolution remote sensing images,which has a certain application prospect.
It is crucial for agricultural production to know crop planting situation.Temporal remote sensing images and subtle spectral characteristics of ground features play an important role in extracting crops distribution.At this point,multi-temporal Landsat 8 OLI images were used to extracting the distribution of main crops in the east of Xinrong district of Datong city by using Spectral Angle Mapper(SAM) combined with the decision tree classification,and the extracting result was compared with the result that maximum likelihood extracted.The results show that:① The planting area of spring corn,grain,soybean and potato is decreased and mosaic distribution in order.② The overall accuracy obtained by SAM combined with the decision tree classification is 85.34% and the Kappa coefficient is 0.76,which is outperformed the results of maximum likelihood with the increase of 22.51% and 0.31,respectively,the classification results was more consistent with the actual distribution of main crops.③ The classification accuracy of main crops used the multi-temporal remote sensing images was obviously higher than that of single-temporal image,and the difference between ground features and spectra in middle or high resolution images can effectively weaken by analyzing multi-temporal data from the perspective of difference of spectral angle.The results not only confirmed the positive effect of multi-temporal remote sensing images on crops classification,but also developed the SAM combined with decision tree classification in crops classification of medium-high resolution remote sensing images,which has a certain application prospect.
引文
[1] Zhang Dongxia,Zhang Jixian,Chang Fan,et al.A Review on Application of Remote Sensing Technology in Main Food Crop Yield Estimation[J].Science of Surveying and Mapping,2014,39(11):95-98.[张东霞,张继贤,常帆,等.遥感技术在主要粮食作物估产中的应用[J].测绘科学,2014,39(11):95-98.]
[2] Hu Qiong,Wu Wenbin,Song Qian,et al.Recent Process in Research of Crop Patterns Mapping by Using Remote Sensing[J].Scientia Agriculture Sinica,2015,48(10):1900-1914.[胡琼,吴文斌,宋茜,等.农作物种植结构遥感提取研究进展[J].中国农业科学,2015,48(10):1900-1914.]
[3] Yang C,Everitt J H,Murden D.Evaluating High Resolution SPOT 5 Satellite Imagery for Crop Identification[J].Computers & Electronics in Agriculture,2011,75(2):347-354.
[4] Yang Chao.Research on Land Use/Land Cover Classification based on Mixed Pixel Decomposition Decision Tree[D].Kunming:Yunnan Normal University,2017,18-29.[杨超.基于混合像元分解决策树的土地利用/覆被分类研究[D].昆明:云南师范大学,2017.18-29.]
[5] Wang Lianxi,Xu Shengnan,Li Qi,et al.Extraction of Winter Wheat Planted Area in Jiangsu Province Using Decision Tree and Mixed-Pixel Methods[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(5):182-187.[王连喜,徐胜男,李琪,等.基于决策树和混合像元分解的江苏省冬小麦种植面积提取[J].农业工程学报,2016,32(5):182-187.]
[6] Zhou Jingping,Li Cunjun,Shi Leigang,et al.Crop Distribution Information Extracted by Remote Sensing based on Decision Tree and Object-oriented Method[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(9):318-326.[周静平,李存军,史磊刚,等.基于决策树和面向对象的作物分布信息遥感提取[J].农业机械学报,2016,47(9):318-326.]
[7] Shi Feifei,Gao Xiaohong,Yang Lingyu,et al.Research on Typical Crop Classification based on HJ-1A Hyperspectral Data in the Huangshui River Basin[J].Remote Sensing Technology and Application,2017,32(2):206-217.[史飞飞,高小红,杨灵玉等.基于HJ-1A高光谱遥感数据的湟水流域典型农作物分类研究[J].遥感技术与应用,2017,32(2):206-217.]
[8] Song Qian.Object-based Image Analysis with Machine Learning Algorithms for Cropping Pattern Mapping Using GF-1/WFV Imagery[D].Beijing:Chinese Academy of Agricultural Sciences,2016.[宋茜.基于GF-1/WFV和面向对象的农作物种植结构提取方法研究[D].北京:中国农业科学院,2016.]
[9] Qi Yongju,Pei Liang,Zhang Zongke,et al.The Study of Remote Sensing Image Analysis Method based on Fuzzy ISODATA Clustering[J].Science of Surveying and Mapping,2017,42(7):139-146.[齐永菊,裴亮,张宗科,等.一种模糊聚类的遥感影像分析方法研究[J].测绘科学,2017,42(7):139-146.]
[10] Zhao Xinmiao,Feng Xiangping,Zhao Tao.Investigation on K-means and SVM Mixed Algorithm for Agriculture Information Classification[J].Computer Technology and Development,2017,27(6):178-182.[赵新苗,冯向萍,赵涛.农业信息分类中K-means与SVM的混合算法研究[J].计算机技术与发展,2017,27(6):178-182.]
[11] Guo Dong.Crop Remote Sensing Classification based on Multi-Source Data in Complex Cropping Structure Area[D].Harbin:Northeast Agricultural University,2017.[郭栋.基于多源数据的复杂种植结构区作物遥感分类[D].哈尔滨:东北农业大学,2017.]
[12] Cai Yaojun,Hua Cui,Lu Yuan.Rules for Crop Extraction on Peak Cluster of Karst Area Using Object-oriented Classification Technology[J].Remote Sensing Information,2015(3):104-110.[蔡耀君,华璀,卢远.峰丛洼地农作物面向对象信息提取规则集[J].遥感信息,2015(3):104-110.]
[13] Kruse F A,Lefkoff A B,Boardman J W,et al.The Spectral Image Processing System(SIPS):Interactive Visualization and Analysis of Imaging Spectrometer Data[C]//American Institute of Physics,1993:192-201.
[14] He Yinghong.LULC(Land Use Land Cover) Research based on Multi-source Remote Sensing Data of Lijiang River Basin[D].Xi’an:Chang’an University,2004.[何映红.基于多源遥感数据的漓江流域地表覆盖分类研究[D].西安:长安大学,2014.]
[15] Kumar P,Gupta D K,Mishra V N,et al.Comparison of Support Vector Machine,Artificial Neural Network,and Spectral Angle Mapper Algorithms for Crop Classification Using LISS IV Data[J].International Journal of Remote Sensing,2015,36(6):1604-1617.
[16] Meriame M,Ali E,Fatiha O,et al.Mapping Forest Species in the Central Middle Atlas of Morocco(Azrou Forest) through Remote Sensing Techniques[J].ISPRS International Journal of Geo-Information,2017,6(9):275-281.
[17] Grzegozewski D M,Johann J A,Uribe-Opazo M A,et al.Mapping Soya Bean and Corn Crops in the State of Paraná,Brazil,Using EVI Images from the MODIS Sensor[J].International Journal of Remote Sensing,2016,37(6):19-38.
[18] Cho M A,Debba P,Mathieu R,et al.Spectral Variability Within Species and Its Effects on Savanna Tree Species Discrimination[C]//Geoscience and Remote Sensing Symposium,2009 IEEE International,IEEE International Geoscience and Remote Sensing Symposium.2010:II-190-II-193.
[19] Zhang Jincheng,Li Jianyuan,Yang Guijun,et al.Monitoring of Winter Wheat Stripe Rust based on the Spectral Knowledge base for TM Images[J].Spectroscopy and Spectral Analysis,2010,30(6):1579-1585.[张竞成,李建元,杨贵军,等.基于光谱知识库的TM影像冬小麦条锈病监测研究[J].光谱学与光谱分析,2010,30(6):1579-1585.]
[20] Li Xiaomei.Study on Classification Method of Forest Type with Multi-angle Hyperspectral Remote Sensing[D].Hohhot:Inner Mongolia Agricultural University,2010.[李小梅.多角度高光谱遥感森林类型分类方法研究[D].呼和浩特:内蒙古农业大学,2010.]
[21] Khaleghi M,Ranjbar H,Shahabpour J,et al.Spectral Angle Mapping,Spectral Information Divergence,and Principal Component Analysis of the ASTER SWIR Data for Exploration of Porphyry Copper Mineralization in the Sarduiyeh Area,Kerman Province,Iran[J].Applied Geomatics,2014,6(1):49-58.
[22] Zhou J P,Li C J,Shi L G,et al.Crops Distribution Information Extracted by Remote Sensing based on Decision Tree and Object-Oriented Method[J].Transactions of the Chinese Society for Agricultural Machinery,2016,12(1):40-56.
[23] Hao Shuang,Chen Yongfu,Liu Hua,et al.Object-oriented Forest Classification of Linzhi County based on CART Decision Tree with Texture Information[J].Remote Sensing Technology and Application,2017,32(2):386-394.[郝泷,陈永富,刘华,等.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.]
[24] Chen Yanli,Mo Weihua,Mo Jianfei,et al.Object-oriented Classification for the Extraction of Rice Planting Area in South[J].Remote Sensing Technology and Application,2011,26(2):163-168.[陈燕丽,莫伟华,莫建飞,等.基于面向对象分类的南方水稻种植面积提取方法[J].遥感技术与应用,2011,26(2):163-168.]
[25] Moughal T A,Yu F.An Automatic Unsupervised Method based on Context-Sensitive Spectral Angle Mapper for Change Detection of Remote Sensing Images[C]//International Conference on Advanced Data Mining and Applications.Springer International Publishing,2014:151-162.
[26] Hashemi T M,Jafari L.Comparison of Spectral Angle Mapping and Spectral Feature Fitting Algorithms in Enhancing the Ophiolite Lithological Units based on the Aster Data(Case-Study:Neyriz Ophiolite Complex)[J].China Illuminating Engineering Journal,2010,2(2):71-86.
[27] Center for the Study of Earth from Space(CSES),1992,SIPS User’s Guide[R].The Spectral Image Processing System,v.1.1,University of Colorado,Boulder,1992:74.
[28] Deschamps B,Mcnairn H,Shang J,et al.Towards Operational Radar-only Crop Type Classification:Comparison of a Traditional Decision Tree with a Random Forest Classifier[J].Canadian Journal of Remote Sensing,2012,38(1):60-68.
[29] Justice C J.Landsat-derived Cropland Mask for Tanzania Using 2010～2013 Time Series and Decision Tree Classifier Methods[C]//AGU Fall Meeting.AGU Fall Meeting Abstracts,2015:3-10.
[30] Li Mingze,Zhang Peiying.Classification of Wetland Vegetation in Hyperspectral Remote Sensing Image based on SAM Algorithm[J].Forest Engineering,2015(2):8-13.[李明泽,张培赢.基于SAM算法的遥感影像湿地植被分类[J].森林工程,2015(2):8-13.]
[2] Hu Qiong,Wu Wenbin,Song Qian,et al.Recent Process in Research of Crop Patterns Mapping by Using Remote Sensing[J].Scientia Agriculture Sinica,2015,48(10):1900-1914.[胡琼,吴文斌,宋茜,等.农作物种植结构遥感提取研究进展[J].中国农业科学,2015,48(10):1900-1914.]
[3] Yang C,Everitt J H,Murden D.Evaluating High Resolution SPOT 5 Satellite Imagery for Crop Identification[J].Computers & Electronics in Agriculture,2011,75(2):347-354.
[4] Yang Chao.Research on Land Use/Land Cover Classification based on Mixed Pixel Decomposition Decision Tree[D].Kunming:Yunnan Normal University,2017,18-29.[杨超.基于混合像元分解决策树的土地利用/覆被分类研究[D].昆明:云南师范大学,2017.18-29.]
[5] Wang Lianxi,Xu Shengnan,Li Qi,et al.Extraction of Winter Wheat Planted Area in Jiangsu Province Using Decision Tree and Mixed-Pixel Methods[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(5):182-187.[王连喜,徐胜男,李琪,等.基于决策树和混合像元分解的江苏省冬小麦种植面积提取[J].农业工程学报,2016,32(5):182-187.]
[6] Zhou Jingping,Li Cunjun,Shi Leigang,et al.Crop Distribution Information Extracted by Remote Sensing based on Decision Tree and Object-oriented Method[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(9):318-326.[周静平,李存军,史磊刚,等.基于决策树和面向对象的作物分布信息遥感提取[J].农业机械学报,2016,47(9):318-326.]
[7] Shi Feifei,Gao Xiaohong,Yang Lingyu,et al.Research on Typical Crop Classification based on HJ-1A Hyperspectral Data in the Huangshui River Basin[J].Remote Sensing Technology and Application,2017,32(2):206-217.[史飞飞,高小红,杨灵玉等.基于HJ-1A高光谱遥感数据的湟水流域典型农作物分类研究[J].遥感技术与应用,2017,32(2):206-217.]
[8] Song Qian.Object-based Image Analysis with Machine Learning Algorithms for Cropping Pattern Mapping Using GF-1/WFV Imagery[D].Beijing:Chinese Academy of Agricultural Sciences,2016.[宋茜.基于GF-1/WFV和面向对象的农作物种植结构提取方法研究[D].北京:中国农业科学院,2016.]
[9] Qi Yongju,Pei Liang,Zhang Zongke,et al.The Study of Remote Sensing Image Analysis Method based on Fuzzy ISODATA Clustering[J].Science of Surveying and Mapping,2017,42(7):139-146.[齐永菊,裴亮,张宗科,等.一种模糊聚类的遥感影像分析方法研究[J].测绘科学,2017,42(7):139-146.]
[10] Zhao Xinmiao,Feng Xiangping,Zhao Tao.Investigation on K-means and SVM Mixed Algorithm for Agriculture Information Classification[J].Computer Technology and Development,2017,27(6):178-182.[赵新苗,冯向萍,赵涛.农业信息分类中K-means与SVM的混合算法研究[J].计算机技术与发展,2017,27(6):178-182.]
[11] Guo Dong.Crop Remote Sensing Classification based on Multi-Source Data in Complex Cropping Structure Area[D].Harbin:Northeast Agricultural University,2017.[郭栋.基于多源数据的复杂种植结构区作物遥感分类[D].哈尔滨:东北农业大学,2017.]
[12] Cai Yaojun,Hua Cui,Lu Yuan.Rules for Crop Extraction on Peak Cluster of Karst Area Using Object-oriented Classification Technology[J].Remote Sensing Information,2015(3):104-110.[蔡耀君,华璀,卢远.峰丛洼地农作物面向对象信息提取规则集[J].遥感信息,2015(3):104-110.]
[13] Kruse F A,Lefkoff A B,Boardman J W,et al.The Spectral Image Processing System(SIPS):Interactive Visualization and Analysis of Imaging Spectrometer Data[C]//American Institute of Physics,1993:192-201.
[14] He Yinghong.LULC(Land Use Land Cover) Research based on Multi-source Remote Sensing Data of Lijiang River Basin[D].Xi’an:Chang’an University,2004.[何映红.基于多源遥感数据的漓江流域地表覆盖分类研究[D].西安:长安大学,2014.]
[15] Kumar P,Gupta D K,Mishra V N,et al.Comparison of Support Vector Machine,Artificial Neural Network,and Spectral Angle Mapper Algorithms for Crop Classification Using LISS IV Data[J].International Journal of Remote Sensing,2015,36(6):1604-1617.
[16] Meriame M,Ali E,Fatiha O,et al.Mapping Forest Species in the Central Middle Atlas of Morocco(Azrou Forest) through Remote Sensing Techniques[J].ISPRS International Journal of Geo-Information,2017,6(9):275-281.
[17] Grzegozewski D M,Johann J A,Uribe-Opazo M A,et al.Mapping Soya Bean and Corn Crops in the State of Paraná,Brazil,Using EVI Images from the MODIS Sensor[J].International Journal of Remote Sensing,2016,37(6):19-38.
[18] Cho M A,Debba P,Mathieu R,et al.Spectral Variability Within Species and Its Effects on Savanna Tree Species Discrimination[C]//Geoscience and Remote Sensing Symposium,2009 IEEE International,IEEE International Geoscience and Remote Sensing Symposium.2010:II-190-II-193.
[19] Zhang Jincheng,Li Jianyuan,Yang Guijun,et al.Monitoring of Winter Wheat Stripe Rust based on the Spectral Knowledge base for TM Images[J].Spectroscopy and Spectral Analysis,2010,30(6):1579-1585.[张竞成,李建元,杨贵军,等.基于光谱知识库的TM影像冬小麦条锈病监测研究[J].光谱学与光谱分析,2010,30(6):1579-1585.]
[20] Li Xiaomei.Study on Classification Method of Forest Type with Multi-angle Hyperspectral Remote Sensing[D].Hohhot:Inner Mongolia Agricultural University,2010.[李小梅.多角度高光谱遥感森林类型分类方法研究[D].呼和浩特:内蒙古农业大学,2010.]
[21] Khaleghi M,Ranjbar H,Shahabpour J,et al.Spectral Angle Mapping,Spectral Information Divergence,and Principal Component Analysis of the ASTER SWIR Data for Exploration of Porphyry Copper Mineralization in the Sarduiyeh Area,Kerman Province,Iran[J].Applied Geomatics,2014,6(1):49-58.
[22] Zhou J P,Li C J,Shi L G,et al.Crops Distribution Information Extracted by Remote Sensing based on Decision Tree and Object-Oriented Method[J].Transactions of the Chinese Society for Agricultural Machinery,2016,12(1):40-56.
[23] Hao Shuang,Chen Yongfu,Liu Hua,et al.Object-oriented Forest Classification of Linzhi County based on CART Decision Tree with Texture Information[J].Remote Sensing Technology and Application,2017,32(2):386-394.[郝泷,陈永富,刘华,等.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.]
[24] Chen Yanli,Mo Weihua,Mo Jianfei,et al.Object-oriented Classification for the Extraction of Rice Planting Area in South[J].Remote Sensing Technology and Application,2011,26(2):163-168.[陈燕丽,莫伟华,莫建飞,等.基于面向对象分类的南方水稻种植面积提取方法[J].遥感技术与应用,2011,26(2):163-168.]
[25] Moughal T A,Yu F.An Automatic Unsupervised Method based on Context-Sensitive Spectral Angle Mapper for Change Detection of Remote Sensing Images[C]//International Conference on Advanced Data Mining and Applications.Springer International Publishing,2014:151-162.
[26] Hashemi T M,Jafari L.Comparison of Spectral Angle Mapping and Spectral Feature Fitting Algorithms in Enhancing the Ophiolite Lithological Units based on the Aster Data(Case-Study:Neyriz Ophiolite Complex)[J].China Illuminating Engineering Journal,2010,2(2):71-86.
[27] Center for the Study of Earth from Space(CSES),1992,SIPS User’s Guide[R].The Spectral Image Processing System,v.1.1,University of Colorado,Boulder,1992:74.
[28] Deschamps B,Mcnairn H,Shang J,et al.Towards Operational Radar-only Crop Type Classification:Comparison of a Traditional Decision Tree with a Random Forest Classifier[J].Canadian Journal of Remote Sensing,2012,38(1):60-68.
[29] Justice C J.Landsat-derived Cropland Mask for Tanzania Using 2010～2013 Time Series and Decision Tree Classifier Methods[C]//AGU Fall Meeting.AGU Fall Meeting Abstracts,2015:3-10.
[30] Li Mingze,Zhang Peiying.Classification of Wetland Vegetation in Hyperspectral Remote Sensing Image based on SAM Algorithm[J].Forest Engineering,2015(2):8-13.[李明泽,张培赢.基于SAM算法的遥感影像湿地植被分类[J].森林工程,2015(2):8-13.]