基于GF-1卫星影像的中国冬小麦制图研究
|
摘要
旨在实现冬小麦面积自动化提取,提出一种基于冬小麦NDVI加权指数(WNDVI)的分类算法。将影像分割成标准的小区域,从而构建冬小麦分类单元,基于WNDVI,采用自适应方法确定冬小麦种植区和非种植区WNDVI分割阈值。以2013年10月至2014年5月期间的GF-1卫星WFV影像为例,构建了全国14个省(市、区)的1180个分类单元的WNDVI,实现了2014年全国主产区冬小麦种植区的空间分布图;采用14233个样本对结果进行验证精度,总体精度达到了90.6%。本方法自动化程度高,结果稳定,适合大范围冬小麦面积监测业务化运行。
To realize the automatically extraction of winter wheat, a classification algorithm based on weighted NDVI index(WNDVI) is proposed to construct the winter wheat classification units. Based on the WNDVI, the division thresholds between winter wheat area and other areas were determined by an adaptive method. Taking GF-1/WFV images from October 2013 to May 2014 as an example, WNDVI from 1180 classification units of14 provinces(city and regions) in China was created. Spatial distribution maps of major winter wheat production areas were produced in 2014. The accuracy verification of the results was conducted with 14233 samples, and the overall accuracy reached 90.6%. The proposed method is highly automated, its results are stable, and it is suitable for large-scale monitoring of winter wheat areas.
To realize the automatically extraction of winter wheat, a classification algorithm based on weighted NDVI index(WNDVI) is proposed to construct the winter wheat classification units. Based on the WNDVI, the division thresholds between winter wheat area and other areas were determined by an adaptive method. Taking GF-1/WFV images from October 2013 to May 2014 as an example, WNDVI from 1180 classification units of14 provinces(city and regions) in China was created. Spatial distribution maps of major winter wheat production areas were produced in 2014. The accuracy verification of the results was conducted with 14233 samples, and the overall accuracy reached 90.6%. The proposed method is highly automated, its results are stable, and it is suitable for large-scale monitoring of winter wheat areas.
引文
[1]Quarmby N A,Milnes M,Hindle T L,et al.The use of multitemporal NDV1 measurements from AVHRR data for crop yield estimation and prediction[J].lnternational Journal of Remote Sensing,1993,14(2):199-210.
[2]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.
[3]Vintrou E,Desbrosse A,Begue A,et al.Crop area mapping in West Africa using landscape stratification of MODIS time series and comparison with existing global land products[J].International Journal of Applied Earth Observation&Geoinformation,2012,14(1):83-93.
[4]Casa C D L,Ovando G G.Estimation of wheat area in Córdoba,Argentina,with multitemporal NDVI data of SPOT-Vegetation[J].International Journal of Geosciences,2013,04(10):1355-1364.
[5]Wardlow B D,Egbert S L.Large-area crop mapping using timeseries MODIS 250m NDVI data:an assessment for the U.S.central great plains[J].Remote Sensing of Environment,2008,112(3):1096-1116.
[6]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(06):17-22.
[7]Jakubauskas M E,Legates D R,Kastens J H.Crop identification using harmonic analysis of time-series AVHRR NDVI data[J].Computers&Electronics in Agriculture,2002,37(1):127-139.
[8]Shakir M,牛铮,王力,等.基于多时相MODIS EVI和临近三年地面数据的新疆作物分类[J].光谱学与光谱分析,2015,35(05):1345-1350.
[9]吴炳方,蒙继华,李强子.国外农情遥感监测系统现状与启示[J].地球科学进展,2010,25(10):1003-1012.
[10]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(5):160-166.
[11]Chellasamy M,Ferre P A T,Humlekrog G M.Automatic training sample selection for a multi-evidence based crop classification approach[J].International Archives of the Photogrammetry Remote Sensing&S,2014,XL-7:63-69.
[12]Pradhan S.Crop area estimation using GIS,remote sensing and area frame sampling[J].International Journal of Applied Earth Observation&Geoinformation,2001,3(1):86-92.
[13]王迪,周清波,刘佳.作物面积空间抽样研究进展[J].中国农业资源与区划,2012(2):9-14.
[14]申克建,何浩,蒙红卫,等.农作物面积空间抽样调查研究进展[J].中国农业资源与区划,2012,33(4):11-16.
[15]焦险峰,杨邦杰,裴志远.基于分层抽样的中国水稻种植面积遥感调查方法研究[J].农业工程学报,2006,22(5):105-110.
[16]Zheng B,Myint S W,Thenkabail P S,et al.A support vector machine to identify irrigated crop types using time-series Landsat NDVI data[J].International Journal of Applied Earth Observation&Geoinformation,2015,34(1):103-112.
[17]Carl A S,Kraft R.Land use classification of ERS-1 images with an artificial neural network[C].Satellite Remote Sensing.International Society for Optics and Photonics,1994:452-459.
[18]刘佳,王利民,季富华,等.农作物种植面积“一张图”遥感监测业务及应用[J].中国农业信息,2018,30(4):77-89.
[19]Lewinski S A.Object-oriented classification of Landsat ETM+satellite image[J].Journal of Water&Land Development,2007,10:91-106.
[20]Song X P,Potapov P V,Krylov A,et al.National-scale soybean mapping and area estimation in the United States using medium resolution satellite imagery and field survey[J].Remote Sensing of Environment,2017,190:383-395.
[21]刘海启,裴志远,张松岭,等.资源一号卫星CCD图像在作物面积监测中的应用[J].农业工程学报,2001,17(4):140-143.
[22]Nagy G,Tolaba J.Nonsupervised crop classification through airborne multispectral observations[J].Ibm Journal of Research&Development,1972,16(2):138-153.
[23]王利民,刘佳,杨福刚,等.基于GF-1卫星遥感的冬小麦面积早期识别[J].农业工程学报2015,31(11):194-201
[24]王利民,刘佳,杨玲波,等.基于NDVI加权指数的冬小麦种植面积遥感监测[J].农业工程学报,2016,32(17):127-135.
[25]王利民,刘佳,高建孟,等.冬小麦面积遥感识别精度与空间分辨率的关系[J].农业工程学报,2016,32(23):152-160
[26]Shi J J,Huang J F,Zhang F.Multi-year monitoring of paddy rice planting area in Northeast China using MODIS time series data[J].Journal of Zhengjiang University-SCIENCE B(Biomedicine&Biotechnology),2013,14(10):934-946
[27]Kontgis C,Schneider A,Ozdogan M.Mapping rice paddy extent and intensification in the Vietnamese Mekong River Delta with dense time stacks of Landsat data[J].Remote Sensing of Environment,2015,169:255-269
[28]Huang J F,Wang X Z,Li X X,et al.Remotely sensed rice yield prediction using multi-temporal NDVI data derived from NOAA'sAVHRR[J].Plos One,2013,8(8):e70816.
[29]Sun H S,Xu A G,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.
[30]Domiri D D.The method for detecting biological parameter of rice growth and early planting of paddy crop by using multi temporal remote sensing data[C]//IOP Conference Series:Earth and Environmental Science.IOP Conference Series:Earth and Environmental Science,2017:012002.
[31]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.
[32]Lu L L,Wang C Z,Guo H D,et al.Detecting winter wheat phenology with SPOT-VEGETATION data in the North China Plain[J].Geocarto International,2014,29(3):244-255.
[2]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.
[3]Vintrou E,Desbrosse A,Begue A,et al.Crop area mapping in West Africa using landscape stratification of MODIS time series and comparison with existing global land products[J].International Journal of Applied Earth Observation&Geoinformation,2012,14(1):83-93.
[4]Casa C D L,Ovando G G.Estimation of wheat area in Córdoba,Argentina,with multitemporal NDVI data of SPOT-Vegetation[J].International Journal of Geosciences,2013,04(10):1355-1364.
[5]Wardlow B D,Egbert S L.Large-area crop mapping using timeseries MODIS 250m NDVI data:an assessment for the U.S.central great plains[J].Remote Sensing of Environment,2008,112(3):1096-1116.
[6]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(06):17-22.
[7]Jakubauskas M E,Legates D R,Kastens J H.Crop identification using harmonic analysis of time-series AVHRR NDVI data[J].Computers&Electronics in Agriculture,2002,37(1):127-139.
[8]Shakir M,牛铮,王力,等.基于多时相MODIS EVI和临近三年地面数据的新疆作物分类[J].光谱学与光谱分析,2015,35(05):1345-1350.
[9]吴炳方,蒙继华,李强子.国外农情遥感监测系统现状与启示[J].地球科学进展,2010,25(10):1003-1012.
[10]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(5):160-166.
[11]Chellasamy M,Ferre P A T,Humlekrog G M.Automatic training sample selection for a multi-evidence based crop classification approach[J].International Archives of the Photogrammetry Remote Sensing&S,2014,XL-7:63-69.
[12]Pradhan S.Crop area estimation using GIS,remote sensing and area frame sampling[J].International Journal of Applied Earth Observation&Geoinformation,2001,3(1):86-92.
[13]王迪,周清波,刘佳.作物面积空间抽样研究进展[J].中国农业资源与区划,2012(2):9-14.
[14]申克建,何浩,蒙红卫,等.农作物面积空间抽样调查研究进展[J].中国农业资源与区划,2012,33(4):11-16.
[15]焦险峰,杨邦杰,裴志远.基于分层抽样的中国水稻种植面积遥感调查方法研究[J].农业工程学报,2006,22(5):105-110.
[16]Zheng B,Myint S W,Thenkabail P S,et al.A support vector machine to identify irrigated crop types using time-series Landsat NDVI data[J].International Journal of Applied Earth Observation&Geoinformation,2015,34(1):103-112.
[17]Carl A S,Kraft R.Land use classification of ERS-1 images with an artificial neural network[C].Satellite Remote Sensing.International Society for Optics and Photonics,1994:452-459.
[18]刘佳,王利民,季富华,等.农作物种植面积“一张图”遥感监测业务及应用[J].中国农业信息,2018,30(4):77-89.
[19]Lewinski S A.Object-oriented classification of Landsat ETM+satellite image[J].Journal of Water&Land Development,2007,10:91-106.
[20]Song X P,Potapov P V,Krylov A,et al.National-scale soybean mapping and area estimation in the United States using medium resolution satellite imagery and field survey[J].Remote Sensing of Environment,2017,190:383-395.
[21]刘海启,裴志远,张松岭,等.资源一号卫星CCD图像在作物面积监测中的应用[J].农业工程学报,2001,17(4):140-143.
[22]Nagy G,Tolaba J.Nonsupervised crop classification through airborne multispectral observations[J].Ibm Journal of Research&Development,1972,16(2):138-153.
[23]王利民,刘佳,杨福刚,等.基于GF-1卫星遥感的冬小麦面积早期识别[J].农业工程学报2015,31(11):194-201
[24]王利民,刘佳,杨玲波,等.基于NDVI加权指数的冬小麦种植面积遥感监测[J].农业工程学报,2016,32(17):127-135.
[25]王利民,刘佳,高建孟,等.冬小麦面积遥感识别精度与空间分辨率的关系[J].农业工程学报,2016,32(23):152-160
[26]Shi J J,Huang J F,Zhang F.Multi-year monitoring of paddy rice planting area in Northeast China using MODIS time series data[J].Journal of Zhengjiang University-SCIENCE B(Biomedicine&Biotechnology),2013,14(10):934-946
[27]Kontgis C,Schneider A,Ozdogan M.Mapping rice paddy extent and intensification in the Vietnamese Mekong River Delta with dense time stacks of Landsat data[J].Remote Sensing of Environment,2015,169:255-269
[28]Huang J F,Wang X Z,Li X X,et al.Remotely sensed rice yield prediction using multi-temporal NDVI data derived from NOAA'sAVHRR[J].Plos One,2013,8(8):e70816.
[29]Sun H S,Xu A G,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.
[30]Domiri D D.The method for detecting biological parameter of rice growth and early planting of paddy crop by using multi temporal remote sensing data[C]//IOP Conference Series:Earth and Environmental Science.IOP Conference Series:Earth and Environmental Science,2017:012002.
[31]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.
[32]Lu L L,Wang C Z,Guo H D,et al.Detecting winter wheat phenology with SPOT-VEGETATION data in the North China Plain[J].Geocarto International,2014,29(3):244-255.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |