基于光谱特征分析的匹配与分类技术研究
|
摘要
与全色、多光谱遥感相比,高光谱遥感最大的优势在于能够对地表覆盖类型进行精细探测。成像光谱仪获取的影像光谱分辨率高,可达10nm:波段众多,能为每个像元提供一条完整且连续的光谱曲线。借助从高光谱影像上反演的光谱曲线,通过与标准的参考光谱进行匹配比较,可以直接识别地物目标属性。论文在总结分析高光谱遥感数据预处理技术和光谱特征增强与定量分析方法的基础上,从相似性测度改进和匹配策略优化两个方面对光谱匹配算法进行了深入的研究,主要取得了以下成果:
1.以地物光谱特征的匹配识别为目标,总结了光谱数据定标、辐射校正和反射率转换等预处理方法,结合地形要素分类体系分析了典型地物的光谱特征;从基于光谱曲线属性探测的角度出发,研究了光谱曲线特征增强和定量参数提取的主要方法。
2.在对高光谱影像模式识别分类方法和光谱匹配技术进行归纳总结的基础上,通过对现有光谱相似性测度的分析和试验比较,提出了一种基于曲线信息熵的光谱相似性测度改进方案。试验表明,与传统的单一测度和简单的综合距离相比,该方法用于光谱匹配能够取得更高的精度和更好的适应性。
3.将尺度空间理论引入高光谱影像分类过程,通过对地物光谱信息进行多尺度观察,提取特定尺度下的光谱曲线特征,结合光谱曲线的整体相关性进行匹配分类。试验结果表明:该算法能减少传统匹配方法由于噪声、成像环境等因素引起的错分,有助于分类识别精度的提高。
4.结合决策树分层匹配的思想,在对地物反射光谱特征进行具体分析的基础上,根据成像区域地物类型的具体特点,构造了层次分析光谱匹配模型。试验结果表明,该方法通过在不同节点处灵活采用不同的特征参量和匹配策略,能够明显提高目标提取的精度和可靠性。
Compared to panchromatic and multi-spectral remote sensing, the greatest advantage of hyperspectral mode rests with its ability of fine detection to the earth's surface. Hyperspectral images have spectral resolution high to 10nm and a great deal of bands, so it can offer a full and continues spectral curve to any pixel. Therefore, with spectral feature coming from hyperspectral images and standard referenced spectrum, we can make use of the technology of spectrum matching to identify the property of covers on the ground directly. On the basis of summarizing and analyzing the methods of hyperspectral data preprocessing, feature boosting and quantitative analysis, this paper progressed the study in depth on two aspect of improving the comparability measure and matching strategy. The accomplishments include:
1. Aiming at matching and recognition to the spectral feature, summarized the spectral data preprocessing methods such as calibration, radiometric correction and reflectivity transformation, analyzed the typical spectral feature combined with topographic feature classification system, and studied the primary means of feature boosting and quantitative parameter extraction to spectrum from the point of the property detection with spectral curves.
2. On the basis of summarizing classical pattern recognitive classification methods and spectrum matching technologies , brought forwards a improving programme to the comparability measure through analysis and comparison with experiments. The result indicated that this programme could acquire higher precision and better adaptability in spectrum matching compared with tranditional single measures and simple integrated distances.
3. Brought the theory of scale space into the classification of hyperspectral images, extracted the spectral feature in special scales and carried on the matching and classification combined with total relativity between spectral curves. The result made it clear that the arithmetic could reduce the error from imaging noise and environment in traditional methods, and help to improve the precision.
4. On the basis of particularly analyzing the spectral reflection and combined with the thinking of matching on different grades from decision tree, constructed a hierarchic structure for spectrum matching according to the character of items in imaging region. The result indicated that this arithmetic could distinctly advance the precision of target extraction, through smartly adopting different feature parameters and matching strategy at different nodes.
1.以地物光谱特征的匹配识别为目标,总结了光谱数据定标、辐射校正和反射率转换等预处理方法,结合地形要素分类体系分析了典型地物的光谱特征;从基于光谱曲线属性探测的角度出发,研究了光谱曲线特征增强和定量参数提取的主要方法。
2.在对高光谱影像模式识别分类方法和光谱匹配技术进行归纳总结的基础上,通过对现有光谱相似性测度的分析和试验比较,提出了一种基于曲线信息熵的光谱相似性测度改进方案。试验表明,与传统的单一测度和简单的综合距离相比,该方法用于光谱匹配能够取得更高的精度和更好的适应性。
3.将尺度空间理论引入高光谱影像分类过程,通过对地物光谱信息进行多尺度观察,提取特定尺度下的光谱曲线特征,结合光谱曲线的整体相关性进行匹配分类。试验结果表明:该算法能减少传统匹配方法由于噪声、成像环境等因素引起的错分,有助于分类识别精度的提高。
4.结合决策树分层匹配的思想,在对地物反射光谱特征进行具体分析的基础上,根据成像区域地物类型的具体特点,构造了层次分析光谱匹配模型。试验结果表明,该方法通过在不同节点处灵活采用不同的特征参量和匹配策略,能够明显提高目标提取的精度和可靠性。
Compared to panchromatic and multi-spectral remote sensing, the greatest advantage of hyperspectral mode rests with its ability of fine detection to the earth's surface. Hyperspectral images have spectral resolution high to 10nm and a great deal of bands, so it can offer a full and continues spectral curve to any pixel. Therefore, with spectral feature coming from hyperspectral images and standard referenced spectrum, we can make use of the technology of spectrum matching to identify the property of covers on the ground directly. On the basis of summarizing and analyzing the methods of hyperspectral data preprocessing, feature boosting and quantitative analysis, this paper progressed the study in depth on two aspect of improving the comparability measure and matching strategy. The accomplishments include:
1. Aiming at matching and recognition to the spectral feature, summarized the spectral data preprocessing methods such as calibration, radiometric correction and reflectivity transformation, analyzed the typical spectral feature combined with topographic feature classification system, and studied the primary means of feature boosting and quantitative parameter extraction to spectrum from the point of the property detection with spectral curves.
2. On the basis of summarizing classical pattern recognitive classification methods and spectrum matching technologies , brought forwards a improving programme to the comparability measure through analysis and comparison with experiments. The result indicated that this programme could acquire higher precision and better adaptability in spectrum matching compared with tranditional single measures and simple integrated distances.
3. Brought the theory of scale space into the classification of hyperspectral images, extracted the spectral feature in special scales and carried on the matching and classification combined with total relativity between spectral curves. The result made it clear that the arithmetic could reduce the error from imaging noise and environment in traditional methods, and help to improve the precision.
4. On the basis of particularly analyzing the spectral reflection and combined with the thinking of matching on different grades from decision tree, constructed a hierarchic structure for spectrum matching according to the character of items in imaging region. The result indicated that this arithmetic could distinctly advance the precision of target extraction, through smartly adopting different feature parameters and matching strategy at different nodes.
引文
[1]罗来平,宫辉力,赵文吉.遥感图像决策树分类器研究与实现[J].遥感信息,2006(3):13
[2]余旭初,冯伍法,林立霞.高光谱--遥感测绘的新机遇[J].测绘科学技术学报,2006,23(2):100-104
[3]田庆久,宫鹏.地物波谱数据库研究现状与发展趋势[J].遥感信息,2002(3)
[4]张良培,张立福.高光谱遥感[M].武汉:武汉大学出版社,2005
[5]万余庆,谭克龙,周日平.高光谱遥感应用研究[M].北京:科学出版社,2006:40-41
[6]童庆禧,张兵,郑兰芬.高光谱遥感的多学科应用[M].北京:电子工业出版社,2006:42
[7]崔廷伟,马毅,张杰.航空高光谱遥感的发展与应用[J].遥感技术与应用,2003,18(2):118-122
[8]徐百辉,大地的辨识密码--高光谱影像[J].科学发展,2007(10)
[9]杨宜.成像光谱仪光谱定标技术[J].红外,2006(8)
[10]VANE GREEN R O,CHRIEN T Getal.The Airborne Visible/Infrared Imaging Spectrometer(AVIRIS)[J].Remote Sensing of Environment,1993,44(2):127-143
[11]闵祥军.MAIS成像光谱仪飞行定标和反射率反演[J].遥感学报,1997
[12]朱福清.机载扫描仪地面数据预处理[J].红外与毫米波学报,1992,227-334
[13]亓雪勇,田庆久.光学遥感大气校正研究进展[J].国土资源遥感,2005(4)
[14]Tanre D,Deroo C,Dahaut P.Description of a computer code to simulate the satellite signal in the solar spectrum:The 5S code[J].Int.J.Remote Sense,1990,11:659-668.
[15]吴传庆,童庆禧,郑兰芬.地面、图像光谱数据的预处理[J].遥感技术与应用,2005,20(5):506-511
[16]Kruse F A.Use of Airborne Imaging Spectrometer Data to Map Minerals Associated with Hydrothennally Altered Rocks in the Northern Grapevine Mountains,Navada and California[J].Remote Sensing of Environment,1988,24:31-51
[17]Green A A,Craig M D.Analysis of Aircraft Spectrometer Data with Logarithmic Residuals[A].Proceedings of the Airborne Imaging Spectrometer Workshop[C].JPL Publication,1985.
[18]Clark,R.N,Swayze,G.A.Mapping minerals,amorphous materials,environmental materials,vegetation,water,ice,and snow,and other materials:The USGS Tricorder Algorithm:in Summaries of the Fifth Annual JPL Airborne Earth Science Workshop,JPL Publication,1995,95-1:39-40
[19]杜华强.荒漠化地区高光谱遥感数据预处理及地物光谱重建的研究[D],哈尔滨:东北林业大学,2002
[20]浦瑞良,宫鹏.高光谱遥感及其应用[M].北京:高等教育出版社,2000:88
[21]张宗贵,王润生,郭大海等.成像光谱岩矿识别方法技术研究和影响因素分析[M].北京:地质出版社,2006:29
[22]甘甫平等.高光谱遥感信息提取与地质应用前景[J].国土资源遥感,2000(9):38-44
[23]J.M.Hunt and D.S.Turner,Determination of mineral constituents of rocks by infrared spectroscopy,Anal.Chem,vol(25):1169-1174
[24]Sunshine J M,Peters C M,Pratt S F.Deconvolution of minerals absorption bands:an improved approach[J].Journal of geophysical research,1990.95(5):6955-5966
[25]童庆禧,张兵,郑兰芬.高光谱遥感--原理、技术与应用[M].北京:高等教育出版社,2006
[26]Clark R N,Roush TL.Reflectance spectroscopy:Quantitative analysis techniques for remote sensing application.Journal of Geographical Research,1984,89(7):6329-6340
[27]谢伯承,薛绪掌等.基于包络线法对土壤光谱特征的提取及其分析[J].土壤学报,2005,42(1):171-175
[28]李旭文.光谱遥感数据波形分析法与应用[J].环境遥感,1992,7(3):216-225
[29]Qiu H,Lain N S,Quattorchi DA.Fractral Characterization of Hyperspectral Imagery[J].PE &RS,1999,65(1):63-71
[30]王宏勇,董广军,唐汉松.海岸带高光谱影像分类技术研究[J].海洋测绘,2006,24(6):20-23
[31]张雄飞.网络环境下高光谱数据库构建及其应用实践[D].北京:中国科学院遥感应用研究所,2003
[32](美)Richard O.Duda,Peter E.Hart,David GStork.模式分类[M].北京:机械工业出版社,2003:68
[33]C.Conese,Fabio Maselli.Use of Error Matrices to improve Area Estimate with Maximum Likelihood Classification Procedures[J].Remote Sensing of Environment,1992(40):113-124
[34]陈述彭.数字地球[M].北京:科学出版社,1999
[35]白继伟.基于高光谱数据库的光谱匹配技术研究[D].北京:中国科学院遥感应用研究所,2002
[36]杜培军.高光谱遥感影像检索理论与方法的研究[R].上海:上海交通大学,2004
[37]Carvalho Jr O A,Meneses P R.Spectral correlation mapper(SCM):An improving spectral angle mapper[C].In:Ninth JPL Airborne Earth Science Workshop.Pasadena:JPL Publication,2000.65-74.
[38]李月臣,陈晋,宫鹏,岳天祥.基于NDVI时间序列数据的土地覆盖变化检测指标设计[J].应用基础与工程科学学报,2005,13(3):261-275
[39]“成像光谱技术在土地动态监测中的应用”课题组.成像光谱技术在土地动态监测中的应用[M].北京:地质出版社,2005:60
[40]杨新,唐宏,宋金玲.基于核方法的光谱角制图模型及其在高光谱图像分割中的应用[J].遥感信息,2005(6):20-23
[41]杜培军,唐宏,方涛.高光谱遥感相似性度量算法与若干新方法研究[J].武汉大学学报·信息科学版,2006,31(2):112-115
[42]包倩,郭平.遥感图像检索中的相似性度量方法比较[J].计算机科学,2004,31(7):62-65
[43]董广军,张永生,戴晨光,邓雪清.基于信息散度特征的高光谱影像识别技术[J].仪器仪表学报,2006,27(6):2091-2092
[44]王钦军.高/多光谱遥感目标识别算法及其在岩性目标提取中的应用[D].北京:中国科学院遥感应用研究所,2006
[45]耿修瑞.高光谱遥感图像目标探测与分类技术研究[D].北京:中科院遥感应用研究所,2005
[46]Clark R.N,Swayze G.A,Wise R Livo,E Hoefen,T Kokaly,R Sutley S.J,USGS digital spectral library splib06a:U.S.Geological Survey,Digital Data Series 231,http://speclab.cr.usgs.gov/spectral.lib06
[47]方圣辉,龚浩.动态调整权重的光谱匹配测度法分类的研究[J].武汉大学学报·信息科学版,2006,31(12),1044-1046
[48]余旭初.模式识别与图像分类[M].北京:解放军出版社,2000:62-63
[49]Sung-Ryong Ha,Byung-Woon Aim,San g-Young Park,Change detection of land-cover from multitemporal KOMPSAT-1 EOC imageries[J],Korean Journal of Remote Sensing,2002,18(1 )
[50]沈庭芳,方子文.数字图像处理及模式识别[M].北京:北京理工大学出版社,1998
[51]T.Linderberg and J.Garding.Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure Image and Vision Computing[J],1997,15(6):415-434
[52]陆军,王润生.一种基于尺度空间理论的直线抽取算法[J].中国图像图形学报,2000,5(8):693-698
[53]T.Linderberg and J.Garding.Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure Image and Vision Computing,1997,15(6):415-434
[54]丁达志.模糊决策树模型及其应用研究[D].大连:大连理工大学,2006
[55]Utgoff P.E.ID5:An Incremental ID3[A].In:Fifth International Conference on Machine Learning.San Mateo,CA,Morgan Kaufmann Publishers,1988:107-120
[56]Fried Mark A,Brodley C E.Decision Tree Classification of Land Cover from Remotely Sensed Data[J].Remote Sensing Environment,1997,61:399-400
[57]林丽群,舒宁.基于决策树的多光谱影像分类研究[J],测绘信息与工程,2006,31(5):1-2
[58]张倩.基于决策树方法的航空高光谱遥感土地覆盖分类研究[D].泰安:山东科技大学,2005
[59]王晋年,张兵,刘建贵.以地物识别和分类为目标的高光谱数据挖掘[J].中国图像图形学报,1999,4(11):957-964
[2]余旭初,冯伍法,林立霞.高光谱--遥感测绘的新机遇[J].测绘科学技术学报,2006,23(2):100-104
[3]田庆久,宫鹏.地物波谱数据库研究现状与发展趋势[J].遥感信息,2002(3)
[4]张良培,张立福.高光谱遥感[M].武汉:武汉大学出版社,2005
[5]万余庆,谭克龙,周日平.高光谱遥感应用研究[M].北京:科学出版社,2006:40-41
[6]童庆禧,张兵,郑兰芬.高光谱遥感的多学科应用[M].北京:电子工业出版社,2006:42
[7]崔廷伟,马毅,张杰.航空高光谱遥感的发展与应用[J].遥感技术与应用,2003,18(2):118-122
[8]徐百辉,大地的辨识密码--高光谱影像[J].科学发展,2007(10)
[9]杨宜.成像光谱仪光谱定标技术[J].红外,2006(8)
[10]VANE GREEN R O,CHRIEN T Getal.The Airborne Visible/Infrared Imaging Spectrometer(AVIRIS)[J].Remote Sensing of Environment,1993,44(2):127-143
[11]闵祥军.MAIS成像光谱仪飞行定标和反射率反演[J].遥感学报,1997
[12]朱福清.机载扫描仪地面数据预处理[J].红外与毫米波学报,1992,227-334
[13]亓雪勇,田庆久.光学遥感大气校正研究进展[J].国土资源遥感,2005(4)
[14]Tanre D,Deroo C,Dahaut P.Description of a computer code to simulate the satellite signal in the solar spectrum:The 5S code[J].Int.J.Remote Sense,1990,11:659-668.
[15]吴传庆,童庆禧,郑兰芬.地面、图像光谱数据的预处理[J].遥感技术与应用,2005,20(5):506-511
[16]Kruse F A.Use of Airborne Imaging Spectrometer Data to Map Minerals Associated with Hydrothennally Altered Rocks in the Northern Grapevine Mountains,Navada and California[J].Remote Sensing of Environment,1988,24:31-51
[17]Green A A,Craig M D.Analysis of Aircraft Spectrometer Data with Logarithmic Residuals[A].Proceedings of the Airborne Imaging Spectrometer Workshop[C].JPL Publication,1985.
[18]Clark,R.N,Swayze,G.A.Mapping minerals,amorphous materials,environmental materials,vegetation,water,ice,and snow,and other materials:The USGS Tricorder Algorithm:in Summaries of the Fifth Annual JPL Airborne Earth Science Workshop,JPL Publication,1995,95-1:39-40
[19]杜华强.荒漠化地区高光谱遥感数据预处理及地物光谱重建的研究[D],哈尔滨:东北林业大学,2002
[20]浦瑞良,宫鹏.高光谱遥感及其应用[M].北京:高等教育出版社,2000:88
[21]张宗贵,王润生,郭大海等.成像光谱岩矿识别方法技术研究和影响因素分析[M].北京:地质出版社,2006:29
[22]甘甫平等.高光谱遥感信息提取与地质应用前景[J].国土资源遥感,2000(9):38-44
[23]J.M.Hunt and D.S.Turner,Determination of mineral constituents of rocks by infrared spectroscopy,Anal.Chem,vol(25):1169-1174
[24]Sunshine J M,Peters C M,Pratt S F.Deconvolution of minerals absorption bands:an improved approach[J].Journal of geophysical research,1990.95(5):6955-5966
[25]童庆禧,张兵,郑兰芬.高光谱遥感--原理、技术与应用[M].北京:高等教育出版社,2006
[26]Clark R N,Roush TL.Reflectance spectroscopy:Quantitative analysis techniques for remote sensing application.Journal of Geographical Research,1984,89(7):6329-6340
[27]谢伯承,薛绪掌等.基于包络线法对土壤光谱特征的提取及其分析[J].土壤学报,2005,42(1):171-175
[28]李旭文.光谱遥感数据波形分析法与应用[J].环境遥感,1992,7(3):216-225
[29]Qiu H,Lain N S,Quattorchi DA.Fractral Characterization of Hyperspectral Imagery[J].PE &RS,1999,65(1):63-71
[30]王宏勇,董广军,唐汉松.海岸带高光谱影像分类技术研究[J].海洋测绘,2006,24(6):20-23
[31]张雄飞.网络环境下高光谱数据库构建及其应用实践[D].北京:中国科学院遥感应用研究所,2003
[32](美)Richard O.Duda,Peter E.Hart,David GStork.模式分类[M].北京:机械工业出版社,2003:68
[33]C.Conese,Fabio Maselli.Use of Error Matrices to improve Area Estimate with Maximum Likelihood Classification Procedures[J].Remote Sensing of Environment,1992(40):113-124
[34]陈述彭.数字地球[M].北京:科学出版社,1999
[35]白继伟.基于高光谱数据库的光谱匹配技术研究[D].北京:中国科学院遥感应用研究所,2002
[36]杜培军.高光谱遥感影像检索理论与方法的研究[R].上海:上海交通大学,2004
[37]Carvalho Jr O A,Meneses P R.Spectral correlation mapper(SCM):An improving spectral angle mapper[C].In:Ninth JPL Airborne Earth Science Workshop.Pasadena:JPL Publication,2000.65-74.
[38]李月臣,陈晋,宫鹏,岳天祥.基于NDVI时间序列数据的土地覆盖变化检测指标设计[J].应用基础与工程科学学报,2005,13(3):261-275
[39]“成像光谱技术在土地动态监测中的应用”课题组.成像光谱技术在土地动态监测中的应用[M].北京:地质出版社,2005:60
[40]杨新,唐宏,宋金玲.基于核方法的光谱角制图模型及其在高光谱图像分割中的应用[J].遥感信息,2005(6):20-23
[41]杜培军,唐宏,方涛.高光谱遥感相似性度量算法与若干新方法研究[J].武汉大学学报·信息科学版,2006,31(2):112-115
[42]包倩,郭平.遥感图像检索中的相似性度量方法比较[J].计算机科学,2004,31(7):62-65
[43]董广军,张永生,戴晨光,邓雪清.基于信息散度特征的高光谱影像识别技术[J].仪器仪表学报,2006,27(6):2091-2092
[44]王钦军.高/多光谱遥感目标识别算法及其在岩性目标提取中的应用[D].北京:中国科学院遥感应用研究所,2006
[45]耿修瑞.高光谱遥感图像目标探测与分类技术研究[D].北京:中科院遥感应用研究所,2005
[46]Clark R.N,Swayze G.A,Wise R Livo,E Hoefen,T Kokaly,R Sutley S.J,USGS digital spectral library splib06a:U.S.Geological Survey,Digital Data Series 231,http://speclab.cr.usgs.gov/spectral.lib06
[47]方圣辉,龚浩.动态调整权重的光谱匹配测度法分类的研究[J].武汉大学学报·信息科学版,2006,31(12),1044-1046
[48]余旭初.模式识别与图像分类[M].北京:解放军出版社,2000:62-63
[49]Sung-Ryong Ha,Byung-Woon Aim,San g-Young Park,Change detection of land-cover from multitemporal KOMPSAT-1 EOC imageries[J],Korean Journal of Remote Sensing,2002,18(1 )
[50]沈庭芳,方子文.数字图像处理及模式识别[M].北京:北京理工大学出版社,1998
[51]T.Linderberg and J.Garding.Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure Image and Vision Computing[J],1997,15(6):415-434
[52]陆军,王润生.一种基于尺度空间理论的直线抽取算法[J].中国图像图形学报,2000,5(8):693-698
[53]T.Linderberg and J.Garding.Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure Image and Vision Computing,1997,15(6):415-434
[54]丁达志.模糊决策树模型及其应用研究[D].大连:大连理工大学,2006
[55]Utgoff P.E.ID5:An Incremental ID3[A].In:Fifth International Conference on Machine Learning.San Mateo,CA,Morgan Kaufmann Publishers,1988:107-120
[56]Fried Mark A,Brodley C E.Decision Tree Classification of Land Cover from Remotely Sensed Data[J].Remote Sensing Environment,1997,61:399-400
[57]林丽群,舒宁.基于决策树的多光谱影像分类研究[J],测绘信息与工程,2006,31(5):1-2
[58]张倩.基于决策树方法的航空高光谱遥感土地覆盖分类研究[D].泰安:山东科技大学,2005
[59]王晋年,张兵,刘建贵.以地物识别和分类为目标的高光谱数据挖掘[J].中国图像图形学报,1999,4(11):957-964