基于分形纹理特征的新疆罗布麻遥感分类
|
摘要
传统遥感影像仅利用光谱信息制约了分类精度,对基于分形提取纹理特征在罗布麻分类中的有效性进行了研究。采用分形中的双毯覆盖模型和传统的灰度共生矩阵(GLCM)方法分别提取了Worldview-2影像的纹理特征,结合光谱信息对影像进行最大似然法分类。比较了双毯覆盖模型中不同大小窗口下提取纹理特征的分类结果。结果显示:加入纹理特征后,较多光谱分类总体分类精度提高了1.21%-8.63%,结合分形纹理较GLCM总体分类精度提高了大约两倍;仅分析罗布麻的精度,引入分形的分类精度提高到99.96%,引入GLCM精度却降低了0.09%-0.12%;使用5×5滑动窗口提取纹理特征的分类效果最好。表明基于分形提取纹理特征的遥感分类能有效提高精度,对于Worldview-2影像罗布麻的识别是可行的。
In order to improve the accuracy of the application of remote sensing image in plant classification beyond the weakness of only using spectral information,the texture features of Apocynum venetum,a typical wild plant in Xinjiang,are extracted based on fractal theory from Worldview-2 satellite images by means of double blanket coverage model which are further analyzed by Gray Level Co-occurrence Matrix(GLCM) methods for its classification.Maximum likelihood method is used to classify the textures,and the classification results from different moving window sizes(3×3,5×5,7×7 and 9×9) are compared.The results show that overall classification precision increased by 1.21% to 8.63% for the texture classification compared to traditional spectral information classification,the precision based on fractal theory is more than twice as much as GLCM based texture classification.The classification accuracy of Apocynum venetum increased to 99.96% when this parameter was combined with fractal-based textures.By contrast,the accuracy reduced by 0.09% to 0.12% with GLCM-based textures,and there is best classification precision when fractal-based texture was extracted with a 5×5 sliding block.Therefore,the textures based on fractal theory could effectively improve the accuracy of Worldview-2 images in plant classification by GLCM and double blanket coverage model.
In order to improve the accuracy of the application of remote sensing image in plant classification beyond the weakness of only using spectral information,the texture features of Apocynum venetum,a typical wild plant in Xinjiang,are extracted based on fractal theory from Worldview-2 satellite images by means of double blanket coverage model which are further analyzed by Gray Level Co-occurrence Matrix(GLCM) methods for its classification.Maximum likelihood method is used to classify the textures,and the classification results from different moving window sizes(3×3,5×5,7×7 and 9×9) are compared.The results show that overall classification precision increased by 1.21% to 8.63% for the texture classification compared to traditional spectral information classification,the precision based on fractal theory is more than twice as much as GLCM based texture classification.The classification accuracy of Apocynum venetum increased to 99.96% when this parameter was combined with fractal-based textures.By contrast,the accuracy reduced by 0.09% to 0.12% with GLCM-based textures,and there is best classification precision when fractal-based texture was extracted with a 5×5 sliding block.Therefore,the textures based on fractal theory could effectively improve the accuracy of Worldview-2 images in plant classification by GLCM and double blanket coverage model.
引文
[1]TUCKER C J,HOLBEN B N,ELGIN J H.Remote sensing of total dry matter accumulation in winter wheat[J].Remote Sensing of Environment,1981,11(6):171-189.
[2]SERRANO L,FILELLA I.Remote sensing of biomass and yield of winter wheat under different nitrogen supplies[J].Crop Science,2000,40(3):723-731.
[3]吴炳方,李强子.基于两个独立抽样框架的农作物种植面积遥感估算方法[J].遥感学报,2004,8(6):551-569.WU B F,LI Q Z.Crop acreage estimation using two individual sampling frameworks with stratification[J].Journal of Remote Sensing,2004,8(6):551-569.
[4]秦其明,陆荣建.分形与神经网络方法在卫星数字图像分类中的应用[J].北京大学学报(自然科学版),2000,36(6):858-864.QIN Q M,LU R J.Satellite image classification based on fractal dimension and neural netwotks[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2000,36(6):858-864.
[5]姚云军,秦其明,张自力,等.高光谱技术在农业遥感中的应用研究进展[J].农业工程学报,2008,24(7):301-306.YAO Y J,QIN Q M,ZHANG Z L,et al.Research progress of hyperspectral technology applied agricultural remote sensing[J].Transactions of CSAE,2008,24(7):301-306.
[6]朱再春,陈联裙,张锦水,等.MODISEVI时间序列数据和光谱角聚类的冬小麦遥感估产分区方法研究[J].光谱学与光谱分析,2012,32(7):1899-1903.ZHU Z C,CHEN L Q,ZHANG J S,et al.Division of winter wheat yield estimation by remote sensing based on MODISEVI time series data and spectral angle clustering[J].Spectroscopy and Spectral Analysis,2012,32(7):1899-1903.
[7]张本刚,陈士林.基于遥感技术的甘草资源调查方法研究[J].中草药,2005,36(10):1548-1551.ZHANG B G,CHEN S L.Resources survey of Glyscyrrhiza uralensis based on remote sensing technique[J].Chinese Traditional and Herbal Drugs,2005,36(10):1548-1551.
[8]周应群,陈士林.基于遥感技术的三七资源调查方法研究[J].中国中药杂志,2005,30(24)::1902-1905.ZHOU Y Q,CHEN S L.Study on the resources survey methods of Panax notogingseng based on remote sensing[J].China Journal of Chinese Materia Medica,2005,30(24):1902-1905.
[9]孙宇章,黄璐琦,郭兰萍,等.遥感技术在中药资源调查中的应用[J].中国现代中药,2006,8(9):7-10,35.SUN Y Z,HUANG L Q,GUO L P,et al.Application of remote sensing technology in traditional Chinese medicine resources survey[J].Modern Chinese Medicine,2006,8(9):7-10,35.
[10]孙宇章,郭兰萍,朱文泉,等.不同生态环境类型药用植物资源的遥感监测方法[J].中国中药杂志,2007,32(14):1490-1492.SUN Y Z,GUO L P,ZHU W Q,et al.Remote sensing monitoring methods for medical plants resource in different types of ecological environment[J].China Journal of Chinese Materia Medica,2007,32(14):1490-1492.
[11]孙宇章,顾晓鹤,阳小琼,等.基于RS和GIS技术的江苏邳州市银杏资源动态变化研究[J].中国中药杂志,2007,32(18):1861-1864.SUN Y Z,GU X H,YANG X Q,et al.Study on dynamical changes of Ginkgo bilobas resources in Pizhou city of Jiangus Provinse base onf RS and GIS[J].China Journal of Chinese Materia Medica,2007,32(18):1861-1864.
[12]孙宇章,郭兰萍,朱文泉,等.道地药材茅苍术的资源遥感监测[J].中国中药杂志,2008,33(4):353-356.SUN Y Z,GUO L P,ZHU W Q,et al.Remote sensing resource monitoring on Atractylodes lancea[J].China Journal of Chinese Materia Medica,2008,33(4):353-356.
[13]娜仁花,郑江华,郭宝林,等.基于PCA和纹理特征的红花种植面积遥感估算[J].中国中药杂志,2013,38(21):3681-3686.NAREN H,ZHENG J H,GUO B L,et al.Mesurement of sown area of safflower based on PCA and texture features classification and remote sensing imagery[J].China Journal of Chinese Materia Medica,2013,38(21):3681-3686.
[14]郑淑丹,郑江华,石明辉,等.基于分形和灰度共生矩阵纹理特征的种植型药用植物遥感分类[J].遥感学报,2014,18(4):868-886.ZHENG S D,ZHENG J H,SHI M H.Classification of cultivated Chinese medicinal plants based on fractal theory and gray level co-occurrence matrix textures[J].Journal of Remote Sensing,2014,18(4):868-886.
[15]MYINT S W.Fractal approaches in texture analysis and classification of remotely sensed data:comparisons with spatial auto correlation techniques and simple descriptive statistics[J].International Journal of Remote Sensing,2003,24(9):1925-1947.
[16]SUN W,XU G,GONG P.Fractal analysis of remote sensing images:A review of methods and applications[J].International Journal of Remote Sensing,2006,27(22):4963-4990.
[17]BERKE J.Using spectral fractal dimension in image classification innovation and advances[J].Computer Science and Engineering,2010,10:237-241.
[18]OHANIAN P P,DUBES R C.Performance evaluation for four classes of texture features[J].Patern Recognition,1992,25(8):819-833.
[19]DUTTA S,DATTA A,CHAKLADAR N D.Detection of tool condition from the turned surface image using an accurate gray level co-occurrence technique[J].Precision Engineering,2012,36(3):458-466.
[20]曾文华.基于灰度共生法和小波变换的遥感影像纹理信息提取[D].长春:东北师范大学,2006.ZENG W H.Texture information extraction in remote sensing imageries with gray level co-occurrence matrix and wavelet transform[D].Changchun:Northeast Normal University,2006.
[21]BARALD A,PARMINGGIAN F.An investication on the texture characteristics associated with gray level co-occurence mateix statistical parameters[J].IEEE Transactions on Geosciences and Remote Sensing,1995,32(2):293-303.
[22]KIM J H,KIM S C,KANG T J.Fractal dimension cooccurrence matrix method for texture classification[C]∥Proceedings of the 2006 IEEE Region 10 Conference TENCON.Hong Kong:IEEE,2006:1-4.
[23]WANG X,GEORGANAS N D,PETRIU E M.Fabric texture analysis using computer vision techniques[J].IEEE Transactions on Instrumentation and Measurement,2011,60(1):44-56.
[24]HUANG G,ZHENG Z.The application of franctal in the classification of image texture[J].Acta Geodaetica et Cartographica Sinica,1995,24(4):283-291.
[25]李厚强,刘政凯,林峰.基于分形理论的航空图像分类方法[J].遥感学报,2001,5(5):353-357.LI H Q,LIU Z K,LIN F.Aerial image classification method based on fractal theory[J].Journal of Remote Sensing,2001,5(5):353-357.
[26]刘小刚,赵慧洁,李娜.基于多重分形谱的高光谱数据特征提取[J].光学学报,2009,29(3):844-848.LIU X G,ZHAO H J,LI N.Feature extraction based on multifractal spectrum for hyperspectral data[J].Acta Optica Sinica,2009,29(3):844-848.
[27]ZOU T,QI D.Overview of the remote sensing identification distinguish based on fractal theory[J].Ship Electronic Engineering,2012,214(4):15-21.
[28]PELEG S,NARORAND J,HARTLEY R,et al.Multiple resolution texture analysis and classification[J].IEEE Transactions on Image Processing,2009,6(4):518-523.
[29]焦蓬蓬,郭依正,刘丽娟,等.灰度共生矩阵纹理特征提取的MATLAB实现[J].计算机技术与发展,2012,22(11):167-175.JIAO P P,GUO Y Z,LIU L J,et al.Implementation of gray level co-occurrence matrix texture feature extraction using MATLAB[J].Computer Technology and Development,2012,22(11):167-175.
[30]宋铁群.基于MATLAB的遥感影像纹理特征分析[J].测绘与空间地理信息,2009,32(2):71-74.SONG T Q.Analysis of remote sensing image texture based on MATLAB[J].Geomatics&Spatial Information Technology,2009,32(2):71-74.
[31]徐文海.基于分形理论的遥感影像纹理分析与分类研究[D].长沙:中南大学,2010:6-19.XU W H.Texture analysis and classification of remote sensing image based on fractal theory[D].Changsha:Central South University,2010:6-19.
[32]黄晶.基于分形维度与灰度共生矩阵的图像分类研究[D].武汉:武汉理工大学,2008:25-40.HUANG J.Image classification based on fractal dimension and co-occurrence[D].Wuhan:Wuhan University of Technology,2008:25-40.
[2]SERRANO L,FILELLA I.Remote sensing of biomass and yield of winter wheat under different nitrogen supplies[J].Crop Science,2000,40(3):723-731.
[3]吴炳方,李强子.基于两个独立抽样框架的农作物种植面积遥感估算方法[J].遥感学报,2004,8(6):551-569.WU B F,LI Q Z.Crop acreage estimation using two individual sampling frameworks with stratification[J].Journal of Remote Sensing,2004,8(6):551-569.
[4]秦其明,陆荣建.分形与神经网络方法在卫星数字图像分类中的应用[J].北京大学学报(自然科学版),2000,36(6):858-864.QIN Q M,LU R J.Satellite image classification based on fractal dimension and neural netwotks[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2000,36(6):858-864.
[5]姚云军,秦其明,张自力,等.高光谱技术在农业遥感中的应用研究进展[J].农业工程学报,2008,24(7):301-306.YAO Y J,QIN Q M,ZHANG Z L,et al.Research progress of hyperspectral technology applied agricultural remote sensing[J].Transactions of CSAE,2008,24(7):301-306.
[6]朱再春,陈联裙,张锦水,等.MODISEVI时间序列数据和光谱角聚类的冬小麦遥感估产分区方法研究[J].光谱学与光谱分析,2012,32(7):1899-1903.ZHU Z C,CHEN L Q,ZHANG J S,et al.Division of winter wheat yield estimation by remote sensing based on MODISEVI time series data and spectral angle clustering[J].Spectroscopy and Spectral Analysis,2012,32(7):1899-1903.
[7]张本刚,陈士林.基于遥感技术的甘草资源调查方法研究[J].中草药,2005,36(10):1548-1551.ZHANG B G,CHEN S L.Resources survey of Glyscyrrhiza uralensis based on remote sensing technique[J].Chinese Traditional and Herbal Drugs,2005,36(10):1548-1551.
[8]周应群,陈士林.基于遥感技术的三七资源调查方法研究[J].中国中药杂志,2005,30(24)::1902-1905.ZHOU Y Q,CHEN S L.Study on the resources survey methods of Panax notogingseng based on remote sensing[J].China Journal of Chinese Materia Medica,2005,30(24):1902-1905.
[9]孙宇章,黄璐琦,郭兰萍,等.遥感技术在中药资源调查中的应用[J].中国现代中药,2006,8(9):7-10,35.SUN Y Z,HUANG L Q,GUO L P,et al.Application of remote sensing technology in traditional Chinese medicine resources survey[J].Modern Chinese Medicine,2006,8(9):7-10,35.
[10]孙宇章,郭兰萍,朱文泉,等.不同生态环境类型药用植物资源的遥感监测方法[J].中国中药杂志,2007,32(14):1490-1492.SUN Y Z,GUO L P,ZHU W Q,et al.Remote sensing monitoring methods for medical plants resource in different types of ecological environment[J].China Journal of Chinese Materia Medica,2007,32(14):1490-1492.
[11]孙宇章,顾晓鹤,阳小琼,等.基于RS和GIS技术的江苏邳州市银杏资源动态变化研究[J].中国中药杂志,2007,32(18):1861-1864.SUN Y Z,GU X H,YANG X Q,et al.Study on dynamical changes of Ginkgo bilobas resources in Pizhou city of Jiangus Provinse base onf RS and GIS[J].China Journal of Chinese Materia Medica,2007,32(18):1861-1864.
[12]孙宇章,郭兰萍,朱文泉,等.道地药材茅苍术的资源遥感监测[J].中国中药杂志,2008,33(4):353-356.SUN Y Z,GUO L P,ZHU W Q,et al.Remote sensing resource monitoring on Atractylodes lancea[J].China Journal of Chinese Materia Medica,2008,33(4):353-356.
[13]娜仁花,郑江华,郭宝林,等.基于PCA和纹理特征的红花种植面积遥感估算[J].中国中药杂志,2013,38(21):3681-3686.NAREN H,ZHENG J H,GUO B L,et al.Mesurement of sown area of safflower based on PCA and texture features classification and remote sensing imagery[J].China Journal of Chinese Materia Medica,2013,38(21):3681-3686.
[14]郑淑丹,郑江华,石明辉,等.基于分形和灰度共生矩阵纹理特征的种植型药用植物遥感分类[J].遥感学报,2014,18(4):868-886.ZHENG S D,ZHENG J H,SHI M H.Classification of cultivated Chinese medicinal plants based on fractal theory and gray level co-occurrence matrix textures[J].Journal of Remote Sensing,2014,18(4):868-886.
[15]MYINT S W.Fractal approaches in texture analysis and classification of remotely sensed data:comparisons with spatial auto correlation techniques and simple descriptive statistics[J].International Journal of Remote Sensing,2003,24(9):1925-1947.
[16]SUN W,XU G,GONG P.Fractal analysis of remote sensing images:A review of methods and applications[J].International Journal of Remote Sensing,2006,27(22):4963-4990.
[17]BERKE J.Using spectral fractal dimension in image classification innovation and advances[J].Computer Science and Engineering,2010,10:237-241.
[18]OHANIAN P P,DUBES R C.Performance evaluation for four classes of texture features[J].Patern Recognition,1992,25(8):819-833.
[19]DUTTA S,DATTA A,CHAKLADAR N D.Detection of tool condition from the turned surface image using an accurate gray level co-occurrence technique[J].Precision Engineering,2012,36(3):458-466.
[20]曾文华.基于灰度共生法和小波变换的遥感影像纹理信息提取[D].长春:东北师范大学,2006.ZENG W H.Texture information extraction in remote sensing imageries with gray level co-occurrence matrix and wavelet transform[D].Changchun:Northeast Normal University,2006.
[21]BARALD A,PARMINGGIAN F.An investication on the texture characteristics associated with gray level co-occurence mateix statistical parameters[J].IEEE Transactions on Geosciences and Remote Sensing,1995,32(2):293-303.
[22]KIM J H,KIM S C,KANG T J.Fractal dimension cooccurrence matrix method for texture classification[C]∥Proceedings of the 2006 IEEE Region 10 Conference TENCON.Hong Kong:IEEE,2006:1-4.
[23]WANG X,GEORGANAS N D,PETRIU E M.Fabric texture analysis using computer vision techniques[J].IEEE Transactions on Instrumentation and Measurement,2011,60(1):44-56.
[24]HUANG G,ZHENG Z.The application of franctal in the classification of image texture[J].Acta Geodaetica et Cartographica Sinica,1995,24(4):283-291.
[25]李厚强,刘政凯,林峰.基于分形理论的航空图像分类方法[J].遥感学报,2001,5(5):353-357.LI H Q,LIU Z K,LIN F.Aerial image classification method based on fractal theory[J].Journal of Remote Sensing,2001,5(5):353-357.
[26]刘小刚,赵慧洁,李娜.基于多重分形谱的高光谱数据特征提取[J].光学学报,2009,29(3):844-848.LIU X G,ZHAO H J,LI N.Feature extraction based on multifractal spectrum for hyperspectral data[J].Acta Optica Sinica,2009,29(3):844-848.
[27]ZOU T,QI D.Overview of the remote sensing identification distinguish based on fractal theory[J].Ship Electronic Engineering,2012,214(4):15-21.
[28]PELEG S,NARORAND J,HARTLEY R,et al.Multiple resolution texture analysis and classification[J].IEEE Transactions on Image Processing,2009,6(4):518-523.
[29]焦蓬蓬,郭依正,刘丽娟,等.灰度共生矩阵纹理特征提取的MATLAB实现[J].计算机技术与发展,2012,22(11):167-175.JIAO P P,GUO Y Z,LIU L J,et al.Implementation of gray level co-occurrence matrix texture feature extraction using MATLAB[J].Computer Technology and Development,2012,22(11):167-175.
[30]宋铁群.基于MATLAB的遥感影像纹理特征分析[J].测绘与空间地理信息,2009,32(2):71-74.SONG T Q.Analysis of remote sensing image texture based on MATLAB[J].Geomatics&Spatial Information Technology,2009,32(2):71-74.
[31]徐文海.基于分形理论的遥感影像纹理分析与分类研究[D].长沙:中南大学,2010:6-19.XU W H.Texture analysis and classification of remote sensing image based on fractal theory[D].Changsha:Central South University,2010:6-19.
[32]黄晶.基于分形维度与灰度共生矩阵的图像分类研究[D].武汉:武汉理工大学,2008:25-40.HUANG J.Image classification based on fractal dimension and co-occurrence[D].Wuhan:Wuhan University of Technology,2008:25-40.