作物遥感识别方法研究现状及展望
|
摘要
作物遥感识别是作物面积提取、长势监测、估产和时空分布研究的前提和基础。遥感识别作物方法多样,优势各异,应用性不同。本文系统梳理了基于光谱特征识别作物、基于纹理特征识别作物、基于物候特征识别作物及其他作物遥感识别的方法,归纳总结了每类方法的原理、优缺点和适用范围,指出了需进一步研究和解决的问题,并对今后的发展方向进行了展望,以期为作物遥感识别方法的应用及作物遥感研究提供参考与支撑。
引文
[1]许文波,田亦陈.作物种植面积遥感提取方法的研究进展[J].云南农业大学学报.2005,1(20):95-98.
[2]高宏宇,张楠楠.基于影像光谱特征的作物识别方法探讨[J].黑龙江科技信息,2012(17):11.
[3]Wardlow B D,Egbert S L.Large-area crop mapping using timeseries MODIS 250 m NDVI data:an assessment for the U.S.Central Great Plains[J].Remote Sensing of Environment.2008,112:1096-1116.
[4]承继承.精确农业技术与应用[M].北京:科学出版社,2004.
[5]陈述彭,赵英时.遥感地学分析[M].北京:测绘出版社,1990.
[6]熊利亚.中国作物遥感动态监测与估产集成系统[M].北京:中国科学技术出版社,1996.
[7]刘东,封志明,杨艳昭,等.中国粮食生产发展特征及土地资源承载力空间格局现状[J].农业工程学报,2011,27(7):1-6.
[8]周成虎,骆剑承.遥感影像地学理解与分析[M].北京:科学出版社,1984.
[9]舒田,岳延滨,李莉婕,等.基于高光谱遥感的农作物识别[J].江苏农业学报,2016,32(6):1310-1314.
[10]濮静娟.遥感图像目视解译原理与方法[M].北京:中国科学技术出版社,1992.
[11]马霭乃.遥感目视解译的基本理论与方法[J].遥感信息,1987(3):26-29.
[12]王猛,姚慧敏,隋学艳,等.一种基于地理信息服务平台的小麦种植面积变化监测方法研究[J].安徽农业科学,2013,41(8):3728-3730.
[13]谢登峰,张锦水,潘耀忠,等.Landsat8和MODIS融合构建高时空分辨率数据识别秋粮作物[J].遥感学报,2015,19(5):791-805.
[14]Azar R,Villa P,Stroppiana D,et al.Assessing in-season crop classification performance using satellite data:a test case in Northern Italy[J].European Journal of Remote Sensing,2016,49:361-380.
[15]许亮,汪权方,陈志杰,等.一种快速区分易混农作物的遥感解译方法[J].地理空间信息,2017,15(1):59-62
[16]Karila K,Nevalainen O,Krooks A,et al.Monitoring changes in rice cultivated area from SAR and optical satellite images in Ben Tre and Tra Vinh provinces in Mekong Delta,Vietnam[J].Remote Sensing,2014,6(5):4090-4108.
[17]赵丽花,李卫国,杜培军.基于多时相HJ卫星的冬小麦面积提取[J].遥感信息,2011(2):41-45.
[18]黄德双.神经网络模式识别系统理论[M].北京:电子工业出版社,1996.
[19]修丽娜,刘湘南.人工神经网络遥感分类方法研究现状及发展趋势探析[J].遥感技术与应用,2003(5):339-345.
[20]Chen Y,Zhang X,Wang X,et al.Extraction of crop planting structure in seasons prone to water logging using Landsat8 OLI and MODIS data[J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(21):165-173.
[21]Pandey A,Mishra A.Application of artificial neural networks in yield prediction of potato crop[J].Russian Agricultural Sciences,2017,43(3):266-272.
[22]王威.基于模糊数学的遥感图像分类研究[D].桂林:桂林理工大学,2012.
[23]赵天杰,李新武,张立新,等.双频多极化SAR数据与多光谱数据融合的作物识别[J].地球信息科学学报,2009,11(1):84-90.
[24]Musande V,Kumar A,Kale K.Cotton crop discrimination using fuzzy classification approach[J].Journal of the Indian Society of Remote Sensing,2012,40(4):589-597.
[25]姜丽华,杨晓蓉.基于决策树分类技术的遥感影像分类方法研究[J].农业网络信息,2009,22(10):34-36.
[26]程良晓,江涛,谈明洪,等.基于NDVI时间序列影像的张掖市农作物种植结构提取[J].地理信息世界,2016,23(4):37-44.
[27]Dong S W,Sun D F,Li H.Crop decision tree classification extraction based on MODIS NDVI in Beijing[J].Advanced Materials Research,2014,9:787-790.
[28]田野,张清,李希灿,等.基于多时相影像的棉花种植信息提取方法研究[J].干旱区研究,2017,34(2):423-430.
[29]Friedl M A,Brodley C E,Strahler A H.Maximizing land cover classification accuracies produced by decision trees at continental to global scales[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(2):969-977.
[30]Wang L,Xu S,Qi L,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.
[31]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.
[32]张顺谦,杨秀蓉.神经网络和分形纹理在夜间云雾分离中的应用[J].遥感学报,2006,10(4):497-501.
[33]刘哲,李智晓,张延宽,等.基于时序EVI决策树分类与高分纹理的制种玉米识别[J].农业机械学报,2015,46(10):321-327.
[34]刘吉凯,钟仕全,徐雅,等.基于多时相GF-1WFV数据的南方丘陵地区甘蔗种植面积提取[J].广东农业科学,2014,41(18):149-154.
[35]Li D,Yang F,Wang X.Study on ensemble crop information extraction of remote sensing images based on SVM and BPNN[J].Journal of the Indian Society of Remote Sensing,2016:1-9.
[36]Zhang C,Jin H,Liu Z,et al.Seed maize identification based on texture analysis of GF remote sensing data[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(21):183-188.
[37]黄秋燕,肖鹏峰,冯学智,等.一种基于TV-Gabor模型的高分辨率遥感图像农田信息提取方法[J].遥感信息,2014,29(2):77-82.
[38]平跃鹏.基于MODIS时间序列地表物候特征分析及作物分类[D].哈尔滨:哈尔滨师范大学,2016.
[39]Li L,Friedl M,Xin Q,etal.Mapping crop cycles in China using MODIS-EVI time series[J].Remote Sensing,2014,6(3):2473-249.
[40]刘吉凯,钟仕全,梁文海.基于多时相Landsat8 OLI影像的作物种植结构提取[J].遥感技术与应用,2015,30(4):776-783.
[41]张焕雪,曹新,李强子,等.基于多时相环境星NDVI时间序列的作物分类研究[J].遥感技术与应用,2015,30(2):304-311.
[42]张健康,程彦培,张发旺,等.基于多时相遥感影像的作物种植信息提取[J].农业工程学报,2012,28(2):134-141.
[43]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.
[44]邓媛媛,巫兆聪,易俐娜,等.面向对象的高分辨率影像农用地分类[J].国土资源遥感,2010,22(4):117-121.
[45]刘明月,王宗明,满卫东,等.基于MODIS时序数据的Landsat8影像选取及面向对象分类方法的农作物分类[J].土壤与作物,2017,6(2):104-112.
[46]Pe1a J,Gutiérrez P,Hervásmartínez C,et al.Object-Based image classification of summer crops with machine learning methods[J].Remote Sensing,2014,6(6):5019-5041.
[47]王娜,李强子,杜鑫,等.单变量特征选择的苏北地区主要农作物遥感识别[J].遥感学报,2017,21(4):519-530.
[48]Sonobe R,Tani H,Wang X,et al.Parameter tuning in the support vector machine and random forest and their performances in crossand same-year crop classification using Terra SAR-X[J].International Journal of Remote Sensing,2014,35(23):7898-7909.
[49]李卫.深度学习在图像识别中的研究及应用[D].武汉:武汉理工大学,2014.
[50]张加楠,张雪芬,简萌,等.先验阈值优化卷积神经网络的作物覆盖度提取算法[J].信号处理,2017,33(9):1230-1238
[51]梁万杰,曹宏鑫.基于卷积神经网络的水稻虫害识别[J].江苏农业科学,2017,45(20):241-243.
[52]Lavreniuk M S.Convolutional neural network for multi-source deep learning crop classification in Ukraine[C]//AGU Fall Meeting.AGU Fall Meeting Abstracts,2016.
[2]高宏宇,张楠楠.基于影像光谱特征的作物识别方法探讨[J].黑龙江科技信息,2012(17):11.
[3]Wardlow B D,Egbert S L.Large-area crop mapping using timeseries MODIS 250 m NDVI data:an assessment for the U.S.Central Great Plains[J].Remote Sensing of Environment.2008,112:1096-1116.
[4]承继承.精确农业技术与应用[M].北京:科学出版社,2004.
[5]陈述彭,赵英时.遥感地学分析[M].北京:测绘出版社,1990.
[6]熊利亚.中国作物遥感动态监测与估产集成系统[M].北京:中国科学技术出版社,1996.
[7]刘东,封志明,杨艳昭,等.中国粮食生产发展特征及土地资源承载力空间格局现状[J].农业工程学报,2011,27(7):1-6.
[8]周成虎,骆剑承.遥感影像地学理解与分析[M].北京:科学出版社,1984.
[9]舒田,岳延滨,李莉婕,等.基于高光谱遥感的农作物识别[J].江苏农业学报,2016,32(6):1310-1314.
[10]濮静娟.遥感图像目视解译原理与方法[M].北京:中国科学技术出版社,1992.
[11]马霭乃.遥感目视解译的基本理论与方法[J].遥感信息,1987(3):26-29.
[12]王猛,姚慧敏,隋学艳,等.一种基于地理信息服务平台的小麦种植面积变化监测方法研究[J].安徽农业科学,2013,41(8):3728-3730.
[13]谢登峰,张锦水,潘耀忠,等.Landsat8和MODIS融合构建高时空分辨率数据识别秋粮作物[J].遥感学报,2015,19(5):791-805.
[14]Azar R,Villa P,Stroppiana D,et al.Assessing in-season crop classification performance using satellite data:a test case in Northern Italy[J].European Journal of Remote Sensing,2016,49:361-380.
[15]许亮,汪权方,陈志杰,等.一种快速区分易混农作物的遥感解译方法[J].地理空间信息,2017,15(1):59-62
[16]Karila K,Nevalainen O,Krooks A,et al.Monitoring changes in rice cultivated area from SAR and optical satellite images in Ben Tre and Tra Vinh provinces in Mekong Delta,Vietnam[J].Remote Sensing,2014,6(5):4090-4108.
[17]赵丽花,李卫国,杜培军.基于多时相HJ卫星的冬小麦面积提取[J].遥感信息,2011(2):41-45.
[18]黄德双.神经网络模式识别系统理论[M].北京:电子工业出版社,1996.
[19]修丽娜,刘湘南.人工神经网络遥感分类方法研究现状及发展趋势探析[J].遥感技术与应用,2003(5):339-345.
[20]Chen Y,Zhang X,Wang X,et al.Extraction of crop planting structure in seasons prone to water logging using Landsat8 OLI and MODIS data[J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(21):165-173.
[21]Pandey A,Mishra A.Application of artificial neural networks in yield prediction of potato crop[J].Russian Agricultural Sciences,2017,43(3):266-272.
[22]王威.基于模糊数学的遥感图像分类研究[D].桂林:桂林理工大学,2012.
[23]赵天杰,李新武,张立新,等.双频多极化SAR数据与多光谱数据融合的作物识别[J].地球信息科学学报,2009,11(1):84-90.
[24]Musande V,Kumar A,Kale K.Cotton crop discrimination using fuzzy classification approach[J].Journal of the Indian Society of Remote Sensing,2012,40(4):589-597.
[25]姜丽华,杨晓蓉.基于决策树分类技术的遥感影像分类方法研究[J].农业网络信息,2009,22(10):34-36.
[26]程良晓,江涛,谈明洪,等.基于NDVI时间序列影像的张掖市农作物种植结构提取[J].地理信息世界,2016,23(4):37-44.
[27]Dong S W,Sun D F,Li H.Crop decision tree classification extraction based on MODIS NDVI in Beijing[J].Advanced Materials Research,2014,9:787-790.
[28]田野,张清,李希灿,等.基于多时相影像的棉花种植信息提取方法研究[J].干旱区研究,2017,34(2):423-430.
[29]Friedl M A,Brodley C E,Strahler A H.Maximizing land cover classification accuracies produced by decision trees at continental to global scales[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(2):969-977.
[30]Wang L,Xu S,Qi L,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.
[31]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.
[32]张顺谦,杨秀蓉.神经网络和分形纹理在夜间云雾分离中的应用[J].遥感学报,2006,10(4):497-501.
[33]刘哲,李智晓,张延宽,等.基于时序EVI决策树分类与高分纹理的制种玉米识别[J].农业机械学报,2015,46(10):321-327.
[34]刘吉凯,钟仕全,徐雅,等.基于多时相GF-1WFV数据的南方丘陵地区甘蔗种植面积提取[J].广东农业科学,2014,41(18):149-154.
[35]Li D,Yang F,Wang X.Study on ensemble crop information extraction of remote sensing images based on SVM and BPNN[J].Journal of the Indian Society of Remote Sensing,2016:1-9.
[36]Zhang C,Jin H,Liu Z,et al.Seed maize identification based on texture analysis of GF remote sensing data[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(21):183-188.
[37]黄秋燕,肖鹏峰,冯学智,等.一种基于TV-Gabor模型的高分辨率遥感图像农田信息提取方法[J].遥感信息,2014,29(2):77-82.
[38]平跃鹏.基于MODIS时间序列地表物候特征分析及作物分类[D].哈尔滨:哈尔滨师范大学,2016.
[39]Li L,Friedl M,Xin Q,etal.Mapping crop cycles in China using MODIS-EVI time series[J].Remote Sensing,2014,6(3):2473-249.
[40]刘吉凯,钟仕全,梁文海.基于多时相Landsat8 OLI影像的作物种植结构提取[J].遥感技术与应用,2015,30(4):776-783.
[41]张焕雪,曹新,李强子,等.基于多时相环境星NDVI时间序列的作物分类研究[J].遥感技术与应用,2015,30(2):304-311.
[42]张健康,程彦培,张发旺,等.基于多时相遥感影像的作物种植信息提取[J].农业工程学报,2012,28(2):134-141.
[43]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.
[44]邓媛媛,巫兆聪,易俐娜,等.面向对象的高分辨率影像农用地分类[J].国土资源遥感,2010,22(4):117-121.
[45]刘明月,王宗明,满卫东,等.基于MODIS时序数据的Landsat8影像选取及面向对象分类方法的农作物分类[J].土壤与作物,2017,6(2):104-112.
[46]Pe1a J,Gutiérrez P,Hervásmartínez C,et al.Object-Based image classification of summer crops with machine learning methods[J].Remote Sensing,2014,6(6):5019-5041.
[47]王娜,李强子,杜鑫,等.单变量特征选择的苏北地区主要农作物遥感识别[J].遥感学报,2017,21(4):519-530.
[48]Sonobe R,Tani H,Wang X,et al.Parameter tuning in the support vector machine and random forest and their performances in crossand same-year crop classification using Terra SAR-X[J].International Journal of Remote Sensing,2014,35(23):7898-7909.
[49]李卫.深度学习在图像识别中的研究及应用[D].武汉:武汉理工大学,2014.
[50]张加楠,张雪芬,简萌,等.先验阈值优化卷积神经网络的作物覆盖度提取算法[J].信号处理,2017,33(9):1230-1238
[51]梁万杰,曹宏鑫.基于卷积神经网络的水稻虫害识别[J].江苏农业科学,2017,45(20):241-243.
[52]Lavreniuk M S.Convolutional neural network for multi-source deep learning crop classification in Ukraine[C]//AGU Fall Meeting.AGU Fall Meeting Abstracts,2016.