一种基于多源多时相遥感信息的城市水稻田分布提取方法
|
摘要
农作物空间监测与提取是城市群区域农业生产与城市发展的重要内容。尽管遥感技术在农业生产中已得到了广泛应用,但长三角地区水稻田监测受多云多雨条件限制,难以获取连续的高质量长时间序列多光谱影像,如何利用多时相多光谱影像及雷达影像高效地提取水稻田空间信息是一个亟须解决的问题。该文提出了一种融合多源多时相遥感影像的水稻田提取方法,以南京市江宁区为研究区域,以GF-1号卫星多光谱影像以及Sentinel-1雷达影像为数据源,选取覆盖水稻生长周期的3个时相雷达影像和3个时相多光谱影像,分别构建多光谱影像特征集(多波段反射率、NDVI、NDWI、EVI等)和雷达影像的反向散射系数特征集,综合实地调查数据选取训练样本,利用粒子群优化的SVM分类器进行分类。结果表明,在多光谱所有特征信息复合中表现最佳的多波段反射率与NDWI、WDRVI组合,再与雷达影像特征组合后,水稻田分类用户精度最高,达到93.42%,平均精度、总体精度和Kappa系数也分别达94.52%、94.31%和0.93。该方法能有效地提取水稻田空间分布信息,同时可为其他作物分类提供参考。
The spatial monitoring and extraction of crops is an important part of agricultural production and urban development under the background of urban agriculture.The current remote sensing technology has been widely used in agricultural production,however,it is difficult to obtain continuous high-quality long-term series images due to the limits restrained by cloudy and rainy conditions,so that how to use a short time series image data to extract the paddy field spatial information effectively is a problem that needed to be solved.In this paper,a method of extracting paddy field by combining multi-source and multi-temporal remote sensing images was developed.The multi-temporal GF-1 and Sentinel-1 radar images of Jiangning District in Nanjing were used as the study data.Then the datasets for the rice extraction were constructed with two parts covering the growth cycle of rice,one is the multiband reflectance(MBR)with their derivative features including the normalized difference vegetation index(NDVI),normalized difference water index(NDWI),enhanced vegetation index(EVI),wide dynamic range vegetation index(WDRVI)and perpendicular vegetation index(PVI)of GF-1 images and the other is the backscattering coefficient and their difference index(BCDI)of Sentinel-1 radar images.Besides,the particle swarm optimization SVM classification approach(PSOSVM)was introduced to extract paddy field and a land survey data was used to validate the classification accuracy.The results show that the combination of MBR,NDWI,WDRVI and BCDI is the best performance in which the rice extraction accuracy reach 93.42%,the average accuracy,overall accuracy and Kappa coefficient reach 94.52%,94.31% and 0.93 respectively.
The spatial monitoring and extraction of crops is an important part of agricultural production and urban development under the background of urban agriculture.The current remote sensing technology has been widely used in agricultural production,however,it is difficult to obtain continuous high-quality long-term series images due to the limits restrained by cloudy and rainy conditions,so that how to use a short time series image data to extract the paddy field spatial information effectively is a problem that needed to be solved.In this paper,a method of extracting paddy field by combining multi-source and multi-temporal remote sensing images was developed.The multi-temporal GF-1 and Sentinel-1 radar images of Jiangning District in Nanjing were used as the study data.Then the datasets for the rice extraction were constructed with two parts covering the growth cycle of rice,one is the multiband reflectance(MBR)with their derivative features including the normalized difference vegetation index(NDVI),normalized difference water index(NDWI),enhanced vegetation index(EVI),wide dynamic range vegetation index(WDRVI)and perpendicular vegetation index(PVI)of GF-1 images and the other is the backscattering coefficient and their difference index(BCDI)of Sentinel-1 radar images.Besides,the particle swarm optimization SVM classification approach(PSOSVM)was introduced to extract paddy field and a land survey data was used to validate the classification accuracy.The results show that the combination of MBR,NDWI,WDRVI and BCDI is the best performance in which the rice extraction accuracy reach 93.42%,the average accuracy,overall accuracy and Kappa coefficient reach 94.52%,94.31% and 0.93 respectively.
引文
[1]SMIT J,RATTA A,NASR J.Urban Agriculture:Food,Jobs and Sustainable Cities[M].NYC:United Nations Development Program,1996.328.
[2]PICKETT S T,CADENASSO M L,GROVE J M,et al.Urban ecological systems:Scientific foundations and a decade of progress[J].Journal of Environmental Management,2011,92(3):331-362.
[3]SAMAD M,MERREY D,VERMILLION D,et al.Irrigation management strategies for improving the performance of irrigated agriculture[J].Outlook on Agriculture,1992,21(4):279-286.
[4]郑长春,王秀珍,黄敬峰.多时相MODIS影像的浙江省水稻种植面积信息提取方法研究[J].浙江大学学报(农业与生命科学版),2009,35(1):98-104.
[5]李卫国,李秉柏,石春林.基于模型和遥感的水稻长势监测研究进展[J].中国农学通报,2006,22(9):457-461.
[6]TENNAKOON S B,MURTY V V N,EIUMNOH A.Estimation of cropped area and grain yield of rice using remote sensing data[J].International Journal of Remote Sensing,1992,13(3):427-439.
[7]KUENZER C,KNAUER K.Remote sensing of rice crop areas[J].International Journal for Remote Sensing,2013,34(6):2101-2139.
[8]唐延林,黄敬峰,王人潮,等.水稻遥感估产模拟模式比较[J].农业工程学报,2004,20(1):166-171.
[9]MANSARAY L,HUANG W,ZHANG D,et al.Mapping rice fields in urban Shanghai,Southeast China,using Sentinel-1A and Landsat 8datasets[J].Remote Sensing,2017,9(3):257-280.
[10]杨艳昭,郑亚南,姜鲁光,等.吉泰盆地水稻熟制遥感识别研究[J].地理与地理信息科学,2014,30(3):16-20.
[11]李喆,胡蝶,赵登忠,等.宽波段遥感植被指数研究进展综述[J].长江科学院院报,2015,32(1):125-130.
[12]徐超,朱秀芳,潘耀忠,等.基于NDII及NDVI提取水稻信息的对比研究[J].地理与地理信息科学,2008,24(5):44-46.
[13]WANG J,XIAO X M,QIN Y W,et al.Mapping paddy rice planting area in wheat-rice double-cropped areas through integration of Landsat-8OLI,MODIS,and PALSAR images[J].Scientific Reports,2015,5:10088.
[14]DAO P D,LIOU Y A.Object-based flood mapping and affected rice field estimation with Landsat 8OLI and MODIS data[J].Remote Sensing,2015,7(5):5077-5097.
[15]JIN C,XIAO X M,DONG J W,et al.Mapping paddy rice distribution using multi-temporal Landsat imagery in the Sanjiang Plain,northeast China[J].Frontiers of Earth Science,2016,10(1):49-62.
[16]李杨,江南,吕恒,等.基于水稻特征波段的决策树分类研究[J].地理与地理信息科学,2010,26(2):11-14.
[17]李志鹏,刘珍环,李正国,等.水稻空间分布遥感提取研究进展与展望[J].中国农业资源与区划,2014,35(6):9-18.
[18]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.
[19]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.
[20]贾玉秋,李冰,程永政,等.基于GF-1与Landsat-8多光谱遥感影像的玉米LAI反演比较[J].农业工程学报,2015,31(9):173-179.
[21]欧阳玲,毛德华,王宗明,等.基于GF-1与Landsat8OLI影像的作物种植结构与产量分析[J].农业工程学报,2017,33(11):147-156.
[22]HAO P Y,WANG L,NIU Z.Potential of multitemporal Gaofen-1panchromatic/multispectral images for crop classification:Case study in Xinjiang Uygur Autonomous Region,China[J].Journal of Applied Remote Sensing,2015,9(1):096035.
[23]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,2015,31(5):160-166.
[24]杨闫君,占玉林,田庆久,等.基于GF-1/WFVNDVI时间序列数据的作物分类[J].农业工程学报,2015,31(24):155-161.
[25]YANG Y J,HUANG Y,TIAN Q J,et al.The extraction model of paddy rice information based on GF-1satellite WFV images[J].Spectroscopy and Spectral Analysis,2015,35(11):3255-3261.
[26]宋盼盼,杜鑫,吴良才,等.基于光谱时间序列拟合的中国南方水稻遥感识别方法研究[J].地球信息科学学报,2017,19(1):117-124.
[27]LECKIE D G,BRAND D G.Advances in remote sensing technologies for forest surveys and management[J].Canadian Journal of Forest Research,1990,20(4):464-483.
[28]雷小雨,卓莉,叶涛,等.基于时差特征与随机森林的水稻种植面积提取[J].遥感技术与应用,2016,31(6):1140-1149.
[29]SHAO Y,FAN X T,LIU H,et al.Rice monitoring and production estimation using multitemporal RADARSAT[J].Remote Sensing of Environment,2001,76(3):310-325.
[30]XUE Z H,DU P J,SU H J.Harmonic analysis for hyperspectral image classification integrated with PSO optimized SVM[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(6):2131-2146.
[31]周义,阮仁宗.多源信息复合的遥感影像水稻田信息提取方法研究[J].遥感信息,2009,24(3):30-33.
[32]ROUSE J W.Monitoring vegetation systems in the great plains with ERTS[J].Nasa Special Publication,1974,1(351):309-317.
[33]GITELSON A A.Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation[J].Journal of Plant Physiology,2004,161(2):165-173.
[34]RICHARDSON A J,WIEGAND C L.Distinguishing vegetation from soil background information[J].Photogrammetric Engineering&Remote Sensing,1977,43(12):1541-1552.
[35]MCFEETERS S K.The use of the normalized difference water index(NDWI)in the delineation of open water features[J].International Journal of Remote Sensing,2012,17(7):1425-1432.
[36]LIU H Q,HUETE A.A feedback based modification of the NDVI to minimize canopy background and atmospheric noise[J].IEEE Transactions on Geoscience&Remote Sensing,1995,33(2):457-465.
[37]NGUYEN D,WAGNER W,NAEIMI V,et al.Rice-planted area extraction by time series analysis of ENVISAT ASAR WS data using a phenology-based classification approach:A case study for Red River Delta,Vietnam[J].International Archives of the Photogrammetry Remote Sensing and Spatial Information Science,2015,40(7):77-83.
[38]NGUYEN D B,GRUBER A,WAGNER W.Mapping rice extent and cropping scheme in the Mekong Delta using Sentinel-1Adata[J].Remote Sensing Letters,2016,7(12):1209-1218.
[39]NGUYEN D B,WAGNER W.European rice cropland mapping with Sentinel-1data:The mediterranean region case study[J].Water,2017,9(6):392-413.
[40]SOUZA C H W D,MERCANTE E,JOHANN J A,et al.Mapping and discrimination of soya bean and corn crops using spectro-temporal profiles of vegetation indices[J].International Journal of Remote Sensing,2015,36(7):1809-1824.
[41]CHANG K W,SHEN Y,LO J C.Predicting rice yield using canopy reflectance measured at booting stage[J].Agronomy Journal,2005,97(3):872-878.
[42]刘瑜,韩震,周玮辰.基于垂直植被指数的湿地植被类型提取研究——以长江口九段沙湿地为例[J].遥感信息,2013,28(4):81-84.
[2]PICKETT S T,CADENASSO M L,GROVE J M,et al.Urban ecological systems:Scientific foundations and a decade of progress[J].Journal of Environmental Management,2011,92(3):331-362.
[3]SAMAD M,MERREY D,VERMILLION D,et al.Irrigation management strategies for improving the performance of irrigated agriculture[J].Outlook on Agriculture,1992,21(4):279-286.
[4]郑长春,王秀珍,黄敬峰.多时相MODIS影像的浙江省水稻种植面积信息提取方法研究[J].浙江大学学报(农业与生命科学版),2009,35(1):98-104.
[5]李卫国,李秉柏,石春林.基于模型和遥感的水稻长势监测研究进展[J].中国农学通报,2006,22(9):457-461.
[6]TENNAKOON S B,MURTY V V N,EIUMNOH A.Estimation of cropped area and grain yield of rice using remote sensing data[J].International Journal of Remote Sensing,1992,13(3):427-439.
[7]KUENZER C,KNAUER K.Remote sensing of rice crop areas[J].International Journal for Remote Sensing,2013,34(6):2101-2139.
[8]唐延林,黄敬峰,王人潮,等.水稻遥感估产模拟模式比较[J].农业工程学报,2004,20(1):166-171.
[9]MANSARAY L,HUANG W,ZHANG D,et al.Mapping rice fields in urban Shanghai,Southeast China,using Sentinel-1A and Landsat 8datasets[J].Remote Sensing,2017,9(3):257-280.
[10]杨艳昭,郑亚南,姜鲁光,等.吉泰盆地水稻熟制遥感识别研究[J].地理与地理信息科学,2014,30(3):16-20.
[11]李喆,胡蝶,赵登忠,等.宽波段遥感植被指数研究进展综述[J].长江科学院院报,2015,32(1):125-130.
[12]徐超,朱秀芳,潘耀忠,等.基于NDII及NDVI提取水稻信息的对比研究[J].地理与地理信息科学,2008,24(5):44-46.
[13]WANG J,XIAO X M,QIN Y W,et al.Mapping paddy rice planting area in wheat-rice double-cropped areas through integration of Landsat-8OLI,MODIS,and PALSAR images[J].Scientific Reports,2015,5:10088.
[14]DAO P D,LIOU Y A.Object-based flood mapping and affected rice field estimation with Landsat 8OLI and MODIS data[J].Remote Sensing,2015,7(5):5077-5097.
[15]JIN C,XIAO X M,DONG J W,et al.Mapping paddy rice distribution using multi-temporal Landsat imagery in the Sanjiang Plain,northeast China[J].Frontiers of Earth Science,2016,10(1):49-62.
[16]李杨,江南,吕恒,等.基于水稻特征波段的决策树分类研究[J].地理与地理信息科学,2010,26(2):11-14.
[17]李志鹏,刘珍环,李正国,等.水稻空间分布遥感提取研究进展与展望[J].中国农业资源与区划,2014,35(6):9-18.
[18]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.
[19]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.
[20]贾玉秋,李冰,程永政,等.基于GF-1与Landsat-8多光谱遥感影像的玉米LAI反演比较[J].农业工程学报,2015,31(9):173-179.
[21]欧阳玲,毛德华,王宗明,等.基于GF-1与Landsat8OLI影像的作物种植结构与产量分析[J].农业工程学报,2017,33(11):147-156.
[22]HAO P Y,WANG L,NIU Z.Potential of multitemporal Gaofen-1panchromatic/multispectral images for crop classification:Case study in Xinjiang Uygur Autonomous Region,China[J].Journal of Applied Remote Sensing,2015,9(1):096035.
[23]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,2015,31(5):160-166.
[24]杨闫君,占玉林,田庆久,等.基于GF-1/WFVNDVI时间序列数据的作物分类[J].农业工程学报,2015,31(24):155-161.
[25]YANG Y J,HUANG Y,TIAN Q J,et al.The extraction model of paddy rice information based on GF-1satellite WFV images[J].Spectroscopy and Spectral Analysis,2015,35(11):3255-3261.
[26]宋盼盼,杜鑫,吴良才,等.基于光谱时间序列拟合的中国南方水稻遥感识别方法研究[J].地球信息科学学报,2017,19(1):117-124.
[27]LECKIE D G,BRAND D G.Advances in remote sensing technologies for forest surveys and management[J].Canadian Journal of Forest Research,1990,20(4):464-483.
[28]雷小雨,卓莉,叶涛,等.基于时差特征与随机森林的水稻种植面积提取[J].遥感技术与应用,2016,31(6):1140-1149.
[29]SHAO Y,FAN X T,LIU H,et al.Rice monitoring and production estimation using multitemporal RADARSAT[J].Remote Sensing of Environment,2001,76(3):310-325.
[30]XUE Z H,DU P J,SU H J.Harmonic analysis for hyperspectral image classification integrated with PSO optimized SVM[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(6):2131-2146.
[31]周义,阮仁宗.多源信息复合的遥感影像水稻田信息提取方法研究[J].遥感信息,2009,24(3):30-33.
[32]ROUSE J W.Monitoring vegetation systems in the great plains with ERTS[J].Nasa Special Publication,1974,1(351):309-317.
[33]GITELSON A A.Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation[J].Journal of Plant Physiology,2004,161(2):165-173.
[34]RICHARDSON A J,WIEGAND C L.Distinguishing vegetation from soil background information[J].Photogrammetric Engineering&Remote Sensing,1977,43(12):1541-1552.
[35]MCFEETERS S K.The use of the normalized difference water index(NDWI)in the delineation of open water features[J].International Journal of Remote Sensing,2012,17(7):1425-1432.
[36]LIU H Q,HUETE A.A feedback based modification of the NDVI to minimize canopy background and atmospheric noise[J].IEEE Transactions on Geoscience&Remote Sensing,1995,33(2):457-465.
[37]NGUYEN D,WAGNER W,NAEIMI V,et al.Rice-planted area extraction by time series analysis of ENVISAT ASAR WS data using a phenology-based classification approach:A case study for Red River Delta,Vietnam[J].International Archives of the Photogrammetry Remote Sensing and Spatial Information Science,2015,40(7):77-83.
[38]NGUYEN D B,GRUBER A,WAGNER W.Mapping rice extent and cropping scheme in the Mekong Delta using Sentinel-1Adata[J].Remote Sensing Letters,2016,7(12):1209-1218.
[39]NGUYEN D B,WAGNER W.European rice cropland mapping with Sentinel-1data:The mediterranean region case study[J].Water,2017,9(6):392-413.
[40]SOUZA C H W D,MERCANTE E,JOHANN J A,et al.Mapping and discrimination of soya bean and corn crops using spectro-temporal profiles of vegetation indices[J].International Journal of Remote Sensing,2015,36(7):1809-1824.
[41]CHANG K W,SHEN Y,LO J C.Predicting rice yield using canopy reflectance measured at booting stage[J].Agronomy Journal,2005,97(3):872-878.
[42]刘瑜,韩震,周玮辰.基于垂直植被指数的湿地植被类型提取研究——以长江口九段沙湿地为例[J].遥感信息,2013,28(4):81-84.