基于多时相影像植被指数变化特征的作物遥感分类
|
摘要
高分一号GF1/WFV遥感影像具有较高的时间和空间分辨率,利用多时相影像开展农作物分类调查具有明显优势。以安徽省颍上县为研究区域,利用2017年5月至9月共6景多时相GF-1/WFV卫星遥感影像数据对主要农作物的分类识别提取。首先,通过分析研究区主要农作物的典型植被指数NDVI、EVI和WDRVI时序变化特征,明析了不同作物在各时相对不同VI的响应特征;其次,基于作物在不同时相的敏感VI变化响应,构建了决策树分层分类模型,成功提取了研究区玉米、水稻、大豆和甘薯四种主要作物种植空间分布情况。结果表明:总体精度达到90.9%,Kappa系数为0.895。同时,采用最大似然法、支持向量机对研究区作物进行分类,通过分类效果对比发现,最大似然法最差,支持向量机次之,决策树分类方法最佳。研究表明:利用多时相时间序列的遥感影像数据,结合作物植被指数特征,采用决策树分类方法可以有效提高作物分类的精度。
GF-1/WFV remote sensing image has higher temporal and spatial resolution. It has obvious advantages to carry out crop classification survey using multiphase images. This paper took Yingshang county of Anhui Province as the study area and extracted main crop classification based on the GF-1/WFV satellite remote sensing image data from May to September 2017. Firstly,through analyzing the sequential variation characteristics of major crops typical vegetation index NDVI,EVI and WDRVI in the study area,made clear the response characteristics of different crops in each time. Then,based on sensitive VI changes of crops in different time phases,the paper constructed decision tree classification model,and successfully extracted the spatial distribution of 4 major crops: corn,rice,soybean and sweet potato in the study area. The results showed that the overall accuracy was 90.9%,and Kappa coefficient was 0.895. At the same time,this paper used the maximum likelihood method,supported vector machine( SVM) for crop classification. The comparison results showed that the maximum likelihood method was the worst,and the support vector machine was second,and the decision tree classification method was the best. Above results indicated that using the remote sensing image data of time series of multi-phase combined with the feature of crop vegetation index,the classification method of decision tree could effectively improve the accuracy of crop classification.
GF-1/WFV remote sensing image has higher temporal and spatial resolution. It has obvious advantages to carry out crop classification survey using multiphase images. This paper took Yingshang county of Anhui Province as the study area and extracted main crop classification based on the GF-1/WFV satellite remote sensing image data from May to September 2017. Firstly,through analyzing the sequential variation characteristics of major crops typical vegetation index NDVI,EVI and WDRVI in the study area,made clear the response characteristics of different crops in each time. Then,based on sensitive VI changes of crops in different time phases,the paper constructed decision tree classification model,and successfully extracted the spatial distribution of 4 major crops: corn,rice,soybean and sweet potato in the study area. The results showed that the overall accuracy was 90.9%,and Kappa coefficient was 0.895. At the same time,this paper used the maximum likelihood method,supported vector machine( SVM) for crop classification. The comparison results showed that the maximum likelihood method was the worst,and the support vector machine was second,and the decision tree classification method was the best. Above results indicated that using the remote sensing image data of time series of multi-phase combined with the feature of crop vegetation index,the classification method of decision tree could effectively improve the accuracy of crop classification.
引文
[1]张峰,吴炳方,刘成林,等.利用时序植被指数监测作物物候的方法研究[J].农业工程学报,2004,20(1):155-159.Zhang F,Wu B F,Liu C L,et al..Research on the method of monitoring crop phenology by using temporal vegetation index[J].Agric.Engin.,2004,20(1):155-159.
[2]郭伟,赵春江,顾晓鹤,等.乡镇尺度的玉米种植面积遥感监测[J].农业工程学报,2011,27(9):69-74.Guo W,Zhao C J,Gu X H,et al..Remote sensing monitoring of maize planting area in township scale[J].Agric.Engin.,2011,27(9):69-74.
[3]贺鹏,徐新刚,张宝雷,等.基于多时相GF-1遥感影像的作物分类提取[J].河南农业科学,2016,45(1):152-159.He P,Xu X G,Zhang B L,et al..The crop classification based on the long-phase GF-1 remote sensing image[J].Henan Agric.Sci.,2016,45(1):152-159.
[4]刘吉凯,钟世全,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):775-783.Liu J K,Zhong S Q,Liang W H.Extraction of crop planting based on the image of Landsat8[J].Remote Sensing Technol.Appl.,2015,30(4):775-783.
[5]许青云,杨贵军,龙慧灵,等.基于MODIS NDVI多年时序数据的农作物种植识别[J].农业工程学报,2014,30(11):134-144.Xu Q Y,Yang G J,Long H L,et al..Identification of crop planting based on MODIS NDVI years of sequential data[J].Agric.Engin.,2014,30(11):134-144.
[6]马丽,徐新刚,刘良云,等.基于多时相NDVI及特征波段的作物分类研究[J].遥感技术与应用,2008,23(5):520-524.Ma L,Xu X G,Liu L Y,et al..Research on crop classification based on time phase NDVI and feature bands[J].Remote Sensing Technol.Appl.,2008,23(5):520-524.
[7]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.Li X C,Xu X G,Wang J H,et al..Crop classification recognition based on time series environmental satellite images[J].Agric.Engin.,2013,29(2):169-176.
[8]Song Q,Zhou Q B,Wu W B,et al..Mapping regional cropping patterns by using GF-1 WFV sensor data[J].Sci.Direct,2017,16(2):337-347.
[9]Zhou Q B,Yu Q Y,Liu J,et al..Perspective of Chinese GF-1high-resolution satellite data in agricultural remote sensing monitoring[J].Sci.Direct,2017,16(2):242-251.
[10]陈思宁,赵艳霞,申双和.基于波谱分析技术的遥感作物分类方法[J].农业工程学报,2012,28(5):154-160.Chen S N,Zhao Y X,Shen S H.The classification of remote sensing crops based on spectrum analysis[J].Agric.Engin.,2012,28(5):154-160.
[11]Wardlow B D,Egbert S L.Large-area crop mapping using time-series MODIS 250m NDVI data:An assessment for the U.S.Central Great Plains[J].Remote Sensing Environ.,2008,112(3):1096-1116.
[12]Wu Z T,Thenkabail P S,Rick M,et al..Seasonal cultivated and fallow cropland mapping using MODIS-based automated cropland classification algorithm[J].J.Appl.Remote Sensing,2014,8(1):397-398.
[13]Pan Y Z,Li L,Zhang J S,et al..Winter wheat area estimation from MODIS-EVI time series data using the crop proportion phenology index[J].Remote Sensing Environ.,2012,119(3):232-242.
[14]黄健熙,侯矞焯,苏伟,等.基于GF-1 WFV数据的玉米与大豆种植面积提取方法[J].农业工程学报,2017,33(7):164-170.Huang J X,Hou Y Z,Su W,et al..Based on GF-1 WFV data of corn and soybean planting area extraction method[J].Agric.Engin.,2013,33(7):164-170.
[15]De Souza C H W,Mercante E,Johann J A,et al..Mapping and discrimination of soya bean and corn crops using spectrotemporal profiles of vegetation indices[J].Int.J.Remote Sensing,2015,36(7):1809-1824.
[16]Zhang M W,Zhou Q B,Chen Z X,et al..Crop discrimination in Northen China with double cropping systems using Fourier analysis of time-series MODIS data[J].Int.J.Appl.Earth Observation Geoinformation,2008,10(4):476-485.
[17]魏新彩,王新生,刘海,等.HJ卫星图像水稻种植面积的识别分析[J].地球信息科学学报,2012,14(3):382-387.Wei X C,Wang X S,Liu H,et al..Identification and analysis of rice planting area of HJ satellite image[J].J.Earth Inform.Sci.,2014,14(3):382-387.
[18]徐新刚,李强子,周万村,等.应用高分辨率遥感影像提取作物种植面积[J].遥感技术与应用,2008,23(1):17-23.Xu X G,Li Q Z,Zhou W C,et al..Application of high resolution remote sensing image extraction plant area[J].Remote Sensing Technol.Appl.,2008,23(1):17-23.
[19]邓书斌.ENVI遥感图像处理方法[M].北京:高等教育出版社,2014,134-164.Deng S B.ENVI Remote Sensing Image Processing Method[M].Beijing:Higher Education Press,2014,134-164.
[20]贾坤,李强子,田亦陈,等.遥感影像分类方法研究进展[J].光谱学与光谱分析,2011,31(10):2618-2623.Jia K,Li Q Z,Tian Y C,et al..The research progress of the classification method of remote sensing image[J].Spectroscopy Spectral Anal.,2011,31(10):2618-2623.
[21]翟天林,金贵,邓祥征,等.基于多源遥感影像融合的武汉市土地利用分类方法研究[J].长江流域资源与环境,2016,25(10):1594-1602.Zhai T L,Jin G,Deng X Z,et al..Research on the classification of land use in wuhan city based on multi-source image fusion[J].Resour.Environ.Yangtze River Basin,2016,25(10):1594-1602.
[2]郭伟,赵春江,顾晓鹤,等.乡镇尺度的玉米种植面积遥感监测[J].农业工程学报,2011,27(9):69-74.Guo W,Zhao C J,Gu X H,et al..Remote sensing monitoring of maize planting area in township scale[J].Agric.Engin.,2011,27(9):69-74.
[3]贺鹏,徐新刚,张宝雷,等.基于多时相GF-1遥感影像的作物分类提取[J].河南农业科学,2016,45(1):152-159.He P,Xu X G,Zhang B L,et al..The crop classification based on the long-phase GF-1 remote sensing image[J].Henan Agric.Sci.,2016,45(1):152-159.
[4]刘吉凯,钟世全,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):775-783.Liu J K,Zhong S Q,Liang W H.Extraction of crop planting based on the image of Landsat8[J].Remote Sensing Technol.Appl.,2015,30(4):775-783.
[5]许青云,杨贵军,龙慧灵,等.基于MODIS NDVI多年时序数据的农作物种植识别[J].农业工程学报,2014,30(11):134-144.Xu Q Y,Yang G J,Long H L,et al..Identification of crop planting based on MODIS NDVI years of sequential data[J].Agric.Engin.,2014,30(11):134-144.
[6]马丽,徐新刚,刘良云,等.基于多时相NDVI及特征波段的作物分类研究[J].遥感技术与应用,2008,23(5):520-524.Ma L,Xu X G,Liu L Y,et al..Research on crop classification based on time phase NDVI and feature bands[J].Remote Sensing Technol.Appl.,2008,23(5):520-524.
[7]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.Li X C,Xu X G,Wang J H,et al..Crop classification recognition based on time series environmental satellite images[J].Agric.Engin.,2013,29(2):169-176.
[8]Song Q,Zhou Q B,Wu W B,et al..Mapping regional cropping patterns by using GF-1 WFV sensor data[J].Sci.Direct,2017,16(2):337-347.
[9]Zhou Q B,Yu Q Y,Liu J,et al..Perspective of Chinese GF-1high-resolution satellite data in agricultural remote sensing monitoring[J].Sci.Direct,2017,16(2):242-251.
[10]陈思宁,赵艳霞,申双和.基于波谱分析技术的遥感作物分类方法[J].农业工程学报,2012,28(5):154-160.Chen S N,Zhao Y X,Shen S H.The classification of remote sensing crops based on spectrum analysis[J].Agric.Engin.,2012,28(5):154-160.
[11]Wardlow B D,Egbert S L.Large-area crop mapping using time-series MODIS 250m NDVI data:An assessment for the U.S.Central Great Plains[J].Remote Sensing Environ.,2008,112(3):1096-1116.
[12]Wu Z T,Thenkabail P S,Rick M,et al..Seasonal cultivated and fallow cropland mapping using MODIS-based automated cropland classification algorithm[J].J.Appl.Remote Sensing,2014,8(1):397-398.
[13]Pan Y Z,Li L,Zhang J S,et al..Winter wheat area estimation from MODIS-EVI time series data using the crop proportion phenology index[J].Remote Sensing Environ.,2012,119(3):232-242.
[14]黄健熙,侯矞焯,苏伟,等.基于GF-1 WFV数据的玉米与大豆种植面积提取方法[J].农业工程学报,2017,33(7):164-170.Huang J X,Hou Y Z,Su W,et al..Based on GF-1 WFV data of corn and soybean planting area extraction method[J].Agric.Engin.,2013,33(7):164-170.
[15]De Souza C H W,Mercante E,Johann J A,et al..Mapping and discrimination of soya bean and corn crops using spectrotemporal profiles of vegetation indices[J].Int.J.Remote Sensing,2015,36(7):1809-1824.
[16]Zhang M W,Zhou Q B,Chen Z X,et al..Crop discrimination in Northen China with double cropping systems using Fourier analysis of time-series MODIS data[J].Int.J.Appl.Earth Observation Geoinformation,2008,10(4):476-485.
[17]魏新彩,王新生,刘海,等.HJ卫星图像水稻种植面积的识别分析[J].地球信息科学学报,2012,14(3):382-387.Wei X C,Wang X S,Liu H,et al..Identification and analysis of rice planting area of HJ satellite image[J].J.Earth Inform.Sci.,2014,14(3):382-387.
[18]徐新刚,李强子,周万村,等.应用高分辨率遥感影像提取作物种植面积[J].遥感技术与应用,2008,23(1):17-23.Xu X G,Li Q Z,Zhou W C,et al..Application of high resolution remote sensing image extraction plant area[J].Remote Sensing Technol.Appl.,2008,23(1):17-23.
[19]邓书斌.ENVI遥感图像处理方法[M].北京:高等教育出版社,2014,134-164.Deng S B.ENVI Remote Sensing Image Processing Method[M].Beijing:Higher Education Press,2014,134-164.
[20]贾坤,李强子,田亦陈,等.遥感影像分类方法研究进展[J].光谱学与光谱分析,2011,31(10):2618-2623.Jia K,Li Q Z,Tian Y C,et al..The research progress of the classification method of remote sensing image[J].Spectroscopy Spectral Anal.,2011,31(10):2618-2623.
[21]翟天林,金贵,邓祥征,等.基于多源遥感影像融合的武汉市土地利用分类方法研究[J].长江流域资源与环境,2016,25(10):1594-1602.Zhai T L,Jin G,Deng X Z,et al..Research on the classification of land use in wuhan city based on multi-source image fusion[J].Resour.Environ.Yangtze River Basin,2016,25(10):1594-1602.