空间光谱差比参量及其模拟应用
|
摘要
针对自然界中广泛存在的光谱特征随空间有规律变化的一类地物在混合像元背景地物的干扰下难以有效识别的问题,提出了基于空间光谱差比参量的识别方法。通过理论分析与公式推导,首先对空间光谱差比参量的概念进行了定义,然后基于图像模拟,通过算法设计应用该参量进行目标识别。结果表明,该参量对于不同目标背景干扰下该类地物的识别具有科学性及有效性,模拟图像的分类识别精度达到了99.8%,随着影像空间分辨率与光谱分辨率的逐步提高,具有一定的应用前景。
Aiming at the problem that it is hard to identify the objects whose spectral feature regularly changes following the space changes by traditional methods,especially under the different sorts of interference in the nature,a new target identification method based on spatial-spectral difference ratio(Vss)parameter was developed.Firstly,we defined the concept of the Vss parameter through theoretical analysis and formula derivation.Secondly,based on image simulation,we used Vssparameter to identify the targets via the designed algorithm.The results show that it is scientific and effective to using the Vssparameter to identify targets which are disturbed by different background.The classification accuracy reached 99.8%in simulation image experiments.It will have certain application prospects with the gradual improvement of the image spatial resolution and spectral resolution.
Aiming at the problem that it is hard to identify the objects whose spectral feature regularly changes following the space changes by traditional methods,especially under the different sorts of interference in the nature,a new target identification method based on spatial-spectral difference ratio(Vss)parameter was developed.Firstly,we defined the concept of the Vss parameter through theoretical analysis and formula derivation.Secondly,based on image simulation,we used Vssparameter to identify the targets via the designed algorithm.The results show that it is scientific and effective to using the Vssparameter to identify targets which are disturbed by different background.The classification accuracy reached 99.8%in simulation image experiments.It will have certain application prospects with the gradual improvement of the image spatial resolution and spectral resolution.
引文
[1]黄慧萍.面向对象影像分析中的尺度问题研究[D].北京:中国科学院研究生院:遥感应用研究所,2003.
[2]韩志刚,孔云峰,秦耀辰.地理表达研究进展[J].地理科学进展,2011,30(2):141-148.
[3]刘天乐.基于高光谱遥感的矿物光谱特征分析和提取[D].武汉:中国地质大学,2009.
[4]谭昌伟,郭文善,王纪华,等.浅析遥感光谱特征参量的原理及基本方法[J].遥感技术与应用,2010,25(1):155-160.
[5]ZHANG C,QIN Q,CHEN L,et al.Rapid determination of coalbed methane exploration target region utilizing hyperspectral remote sensing[J].International Journal of Coal Geology,2015,150/151:19-34.
[6]JIA J,YANG N,ZHANG C,et al.Object-oriented feature selection of high spatial resolution images using improved relief algorithm[J].Mathematical and Computer Modelling,2013,58(3/4):619-626.
[7]秦昆,陈一祥,甘顺子,等.高分辨率遥感影像空间结构特征建模方法综述[J].中国图象图形学报,2013,18(9):1055-1064.
[8]鲁学军,王钦敏,明冬萍,等.空间特征在遥感影像分析中的应用[J].中国图象图形学报,2004,9(6):97-103.
[9]WANG L,HAO S,WANG Q,et al.Semi-supervised classification for hyperspectral imagery based on spatial-spectral label propagation[J].ISPRS J Photogramm,2014,97:123-137.
[10]YANG J,LI P.Impervious surface extraction in urban areas from high spatial resolution imagery using linear spectral unmixing[J].Remote Sensing Applications:Society and Environment,2015,1:61-71.
[11]余柏蒗.基于面向对象理论的城市空间信息遥感分析研究[D].上海:华东师范大学,2009.
[2]韩志刚,孔云峰,秦耀辰.地理表达研究进展[J].地理科学进展,2011,30(2):141-148.
[3]刘天乐.基于高光谱遥感的矿物光谱特征分析和提取[D].武汉:中国地质大学,2009.
[4]谭昌伟,郭文善,王纪华,等.浅析遥感光谱特征参量的原理及基本方法[J].遥感技术与应用,2010,25(1):155-160.
[5]ZHANG C,QIN Q,CHEN L,et al.Rapid determination of coalbed methane exploration target region utilizing hyperspectral remote sensing[J].International Journal of Coal Geology,2015,150/151:19-34.
[6]JIA J,YANG N,ZHANG C,et al.Object-oriented feature selection of high spatial resolution images using improved relief algorithm[J].Mathematical and Computer Modelling,2013,58(3/4):619-626.
[7]秦昆,陈一祥,甘顺子,等.高分辨率遥感影像空间结构特征建模方法综述[J].中国图象图形学报,2013,18(9):1055-1064.
[8]鲁学军,王钦敏,明冬萍,等.空间特征在遥感影像分析中的应用[J].中国图象图形学报,2004,9(6):97-103.
[9]WANG L,HAO S,WANG Q,et al.Semi-supervised classification for hyperspectral imagery based on spatial-spectral label propagation[J].ISPRS J Photogramm,2014,97:123-137.
[10]YANG J,LI P.Impervious surface extraction in urban areas from high spatial resolution imagery using linear spectral unmixing[J].Remote Sensing Applications:Society and Environment,2015,1:61-71.
[11]余柏蒗.基于面向对象理论的城市空间信息遥感分析研究[D].上海:华东师范大学,2009.