基于纹理及光谱信息融合的遥感图像分类方法研究
|
摘要
本文研究了一种基于光谱特征及纹理特征融合的遥感图像分类方法。
在本文设计的分类方法中,首先提出了一种新的适用于遥感目标分类的目标特征——幅度波谱向量,并把该特征和纹理特征进行融合,对特征分量进行逐点自适应加权,然后设计了一种性能良好的具有降维功能的隶属函数对目标的真实特征值进行投影变换,使其成为模糊特征值。然后,选定分类规则对目标进行分类,最后,对分类结果采用两种方法进行评价。
对遥感图像进行实验分析,首先用本文提出的方法对不同复杂程度的仿真图像进行分类实验,并和基于不同特征的分类方法进行比较。其次是对融合前后的实际图像进行实验,比较其分类结果。最后对采用9种不同融合方法得到的图像用本文提出的方法进行分类,比较融合方法的好坏。
通过实验分析,采用本文提出的方法,即有加权系数的特征融合方法,进行仿真实验,用全局评价的方法进行评估,对三类的图像,总体分类精度为92.60%。而采用未改进的方法,即没有加权系数的特征融合方法,其总体分类精度为78.48%；对五类的图像,用本文提出的方法,即有加权系数的特征融合方法,进行仿真实验,用全局评价的方法进行评估,总体分类精度为91.12%,而采用未改进的方法,即没有加权系数的特征融合方法,其总体分类精度为90.67%。
对采用9种不同融合方法得到的图像进行分类,其分类结果明显好于融合前的图像。对于三类图像,融合前图像的分类精度为90.77%,而采用9种融合方法得到的图像的平均精度为92.62%；对于五类图像,融合前图像的分类精度为88.99%,而采用9种融合方法得到的图像的平均精度为90.82%。
实验结果表明：新的分类方法能够获得比当前的典型处理方法性能更好的识别效果,同时融合后的图像比融合前的图像分类效果更好。
A new remote sensing object classification algorithm based on the fusion of texture feature and spectral feature is proposed.
In the classification algorithm which is prompted in this paper, a new kind of target feature named feature spectrum vector is put forward here. Meanwhile, a new kind of feature fusion method that based on vector relativity is prompted here. And then, a new membership function with better performance and the decreasing dimension function is promoted here. Using this function to make projection transformation to the real feature, then the fuzzy feature value can be received. And then, choose a kind of classify rule, and label the targets. At last, the classification results are evaluated by two different methods.
Remote sensing images are experimented using the promoted classification algorithm proposed in this paper. First, simulation images of different levels of complexity are experimented and compared with different classification methods based on different features. Second, original image and fusion image are experimented and compare the classification results. Last, use the promoted algorithm to assort experiment of remote sensing images with nine different fusion methods and compare the classification results.
Through the experimental analysis, use the promoted algorithm, ie feature fusion with the weighting coefficients, to assort experiment of real remote sensing images. For three kinds of iamge, the overall classification accuracy is 92.60%. But using the unimproved algorithm, ie feature fusion without the weighting coefficients, the overall classification accuracy is 90.15%. For five kinds of iamge, use the promoted algorithm, ie feature fusion with the weighting coefficients, to assort experiment of real remote sensing images, the overall classification accuracy is 91.11%. But using the unimproved algorithm, ie feature fusion without the weighting coefficients, the overall classification accuracy is 87.58%.
The images on the use of 9 different fusion methods are classified that the classification results significantly better than before the fusion images. For three kinds of no fusion iamge, the overall classification accuracy is 90.77%, but for the fusion image, the overall classification accuracy is 92.62%; For five kinds of no fusion iamge, the overall classification accuracy is 88.99%, but for the fusion image, the overall classification accuracy is 90.82%.
The result suggests that the promoted algorithm can achieve better classification performance. Meanwhile, the classification results of the fusion images significantly better than before the fusion images.
在本文设计的分类方法中,首先提出了一种新的适用于遥感目标分类的目标特征——幅度波谱向量,并把该特征和纹理特征进行融合,对特征分量进行逐点自适应加权,然后设计了一种性能良好的具有降维功能的隶属函数对目标的真实特征值进行投影变换,使其成为模糊特征值。然后,选定分类规则对目标进行分类,最后,对分类结果采用两种方法进行评价。
对遥感图像进行实验分析,首先用本文提出的方法对不同复杂程度的仿真图像进行分类实验,并和基于不同特征的分类方法进行比较。其次是对融合前后的实际图像进行实验,比较其分类结果。最后对采用9种不同融合方法得到的图像用本文提出的方法进行分类,比较融合方法的好坏。
通过实验分析,采用本文提出的方法,即有加权系数的特征融合方法,进行仿真实验,用全局评价的方法进行评估,对三类的图像,总体分类精度为92.60%。而采用未改进的方法,即没有加权系数的特征融合方法,其总体分类精度为78.48%；对五类的图像,用本文提出的方法,即有加权系数的特征融合方法,进行仿真实验,用全局评价的方法进行评估,总体分类精度为91.12%,而采用未改进的方法,即没有加权系数的特征融合方法,其总体分类精度为90.67%。
对采用9种不同融合方法得到的图像进行分类,其分类结果明显好于融合前的图像。对于三类图像,融合前图像的分类精度为90.77%,而采用9种融合方法得到的图像的平均精度为92.62%；对于五类图像,融合前图像的分类精度为88.99%,而采用9种融合方法得到的图像的平均精度为90.82%。
实验结果表明：新的分类方法能够获得比当前的典型处理方法性能更好的识别效果,同时融合后的图像比融合前的图像分类效果更好。
A new remote sensing object classification algorithm based on the fusion of texture feature and spectral feature is proposed.
In the classification algorithm which is prompted in this paper, a new kind of target feature named feature spectrum vector is put forward here. Meanwhile, a new kind of feature fusion method that based on vector relativity is prompted here. And then, a new membership function with better performance and the decreasing dimension function is promoted here. Using this function to make projection transformation to the real feature, then the fuzzy feature value can be received. And then, choose a kind of classify rule, and label the targets. At last, the classification results are evaluated by two different methods.
Remote sensing images are experimented using the promoted classification algorithm proposed in this paper. First, simulation images of different levels of complexity are experimented and compared with different classification methods based on different features. Second, original image and fusion image are experimented and compare the classification results. Last, use the promoted algorithm to assort experiment of remote sensing images with nine different fusion methods and compare the classification results.
Through the experimental analysis, use the promoted algorithm, ie feature fusion with the weighting coefficients, to assort experiment of real remote sensing images. For three kinds of iamge, the overall classification accuracy is 92.60%. But using the unimproved algorithm, ie feature fusion without the weighting coefficients, the overall classification accuracy is 90.15%. For five kinds of iamge, use the promoted algorithm, ie feature fusion with the weighting coefficients, to assort experiment of real remote sensing images, the overall classification accuracy is 91.11%. But using the unimproved algorithm, ie feature fusion without the weighting coefficients, the overall classification accuracy is 87.58%.
The images on the use of 9 different fusion methods are classified that the classification results significantly better than before the fusion images. For three kinds of no fusion iamge, the overall classification accuracy is 90.77%, but for the fusion image, the overall classification accuracy is 92.62%; For five kinds of no fusion iamge, the overall classification accuracy is 88.99%, but for the fusion image, the overall classification accuracy is 90.82%.
The result suggests that the promoted algorithm can achieve better classification performance. Meanwhile, the classification results of the fusion images significantly better than before the fusion images.
引文
[1]刘扬.遥感图像中的多源信息融合技术研究.武汉理工大学.2007,9.2-9
[2]杜凤兰,田庆久,夏学齐.遥感图像分类方法评析与展望.遥感技术与应用.2004.12,19(6).521-523
[3]Qian yin, Ping guo. Multispectral remote sensing image classification with multiple features. Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, Hong Kong,19-22 August 2007
[4]王一达,沈熙玲,谢炯.遥感图像分类方法综述.遥感信息.2006,5,68-69
[5]Jon Atli Benediktsson, Ioannis Kanellopoulos. Classification of Multisource and Hyperspectral Data Based on Decision Fusion. IEEE transactions on geoscience and remote sensing.1999.3,37(3)
[6]那彦.基于多分辨分析理论的图像融合方法.西安电子科技大学出版社.2007,5.135-157
[7]张文君.基于特征库和模糊技术的遥感图像分类研究.电子科技大学.2007.5，3-7
[8]Wen-jie Wang, Zhong-ming Zhao, Hai-qing Zhu. Object-oriented Multi-feature Fusion Change Detection Method for High Resolution Remote Sensing Image, 2009 Urban Remote Sensing Joint Event.IEEE,2009
[9]曾建航,魏萌,王靳辉等.基于知识的遥感影像模糊分类方法.测绘科学技术学报.2008,6,25(3).172-173
[10]郑孝勇,姚景顺,黄小毛等.基于D-S推理的模糊模式识别方法.系统工程与电子技术.2003,25(4).422-424
[11]刘安斐,李弼程,张先飞.基于数据融合的多特征遥感图像分类.数据采集与处理.2006,12,21(4).465-466
[12]胡文元,聂倩,黄小川.基于纹理和光谱信息的高分辨率遥感影像分类.测绘信息与工程.2009,34(1).16-17
[13]Ketut Wikantika, Wihartini, Ryutaro Tateishi. Spectral and Textural Information of Multisensor Data for Land Use Classification in Metropolitan Area, Japan,2000
[14]袁礼海,宋建社,薛文通等.利用灰度和纹理特征的SAR图像分类研究.电光与控制.2007,8,14(4).58-62
[15]林剑,王润生,鲍光淑.基于空间模糊纹理光谱的多光谱遥感图像分类方法.中国图象图形学报.2006,2,11(2).186-191
[16]吴学军.城市TM遥感图像分类方法研究.广西师范大学.2007,4.6-10
[17]王惠明,史萍.纹理特征的提取方法.国传媒大学学报自然科学版.2006,3,13(1).49-51
[18]杨利民,胡龙华,罗铁良等.常用的几种遥感图像特征提取技术分析.中国高新技术企业.2009,112(1).131-132
[19]刘丽,匡纲要.图像纹理特征提取方法综述.中国图象图形学报.2009,4,14(4).625-626
[20]刘新华,舒宁.纹理特征在多光谱遥感影像分类中的应用.测绘信息与工程.2006,31(3).31-32
[21]赵波,孙即祥,张学庆等.一种基于数据融合的遥感目标识别算法.无线电工程.2004,34(12).32-35
[22]王晓东,王荣芝.傅立叶变换在图像处理中的应用.牡丹江师范学院学报.2003，3.22-23
[23]张若岚,刘劲松.图像信号的频域理解.数字电视与数字视频.2002,237(3).12-15
[24]王冲.基于融合技术的遥感图像分类方法研究.西安电子科技大学学报.2009,3.13-15
[25]谭湘莹,于秀兰,钱国蕙.一种大小窗口结合的SAR图像纹理特征分类方法.系统工程与电子技术.2000,22(4).15-17
[26]游代安,余旭初,王建荣.一种基于知识的遥感图像模糊分类算法.工程图学报.2001,115-117
[27]侯海苗,冀小平.基于灰度共生矩阵的纹理特征.长治学院学报.2008,10,25(5).31-32
[28]丁胜峰.基于模糊推理的多源图像融合研究.南京理工大学.2004
[29]崔宇红,倪国强,范宏深.基于模糊推理的纹理图像融合方法研究.光学技术.2005.1,31(1).130-132
[30]Yan Wang, MO Jamshidi. Fuzzy Logic Applied in Remote Sensing Image Classification.2004
[31]党宏社,韩崇昭,王立琦等.基于模糊推理原理的多传感器数据融合方法.仪器仪表学报.2004,8,25(4).528
[32]Fang-ju Wang. Fuzzy Supervised Classification of Remote Sensing Images. IEEE transactions on geoscience and remote sensing.1990.4,28(2)
[33]韩金舫,桑琳,储毅.模糊控制中隶属函数的构造策略.交通与计算机.2001，6.11-12
[34]许将军.高光谱遥感图像特征提取及分类研究.电子科技大学.2007,4.10-15
[35]Marie-Catherine Mouchot, Basel Solaiman, Alfonso Parra. Use of fuzzy logic for unsupervised classification of remotely sensed images.1994
[36]刘宏兵,郭红建,刘道华.一种基于模糊推理的因素权重确定方法.大学数学.2006,6,22(3).139-143
[37]孟艳平.基于相似度的信息权重模糊推理方法.北京师范大学学报(自然科版).2008,42(1).21-24
[38]王海江,陈瑾,徐卫忠.基于Matlab编程方法实现模糊推理及解模糊的方法研究.现代电子技术.2004,190(23).45-46
[39]Yindi Zhao, Liangpei Zhang, Pingxiang Li. Texture Feature Fusion for High Resolution Satellite Image Classification. Proceeding of the Computer Graphics. Imaging and Vision:New Trends.2005
[40]李项军,黄旭华.基于最大隶属度原则的多传感器身份融合.电光与控制.2007.4,14(2).21-23
[41]Jun-ping Zhang, Ye-Zhang,Bin ZOU, Ting-xian Zhou. Fusion Classification of Hyperspectral Image Based On Adaptive Subspace Decomposition. IEEE,2000
[42]刘旭拢,何春阳,潘耀忠等.遥感图像分类精度的点、群样本检验与评估.遥感学报.2006,5,10(3).367
[43]Vassilis Tsagaris, Vassilis Anastassopoulos, George A. Lampropoulos. Fusion of Hyperspectral Data Using Segmented PCT for Color Representation and Classification. IEEE transactions on geoscience and remote sensing, 2005.10,43(10)
[44]吴健平,杨星卫.遥感数据分类结果的精度分析.遥感技术与应用.1995.2,10(1).19-20
[45]陈万海,赵春晖,刘春红.超谱遥感图像的模糊最大似然分类研究.哈尔滨工程大学学报.2006,10,24(5).774
[46]Wenjie Chen, Lihua Dou, Jie Chen. A Target Recognition Method Based on Feature Level Data Fusion. Proceeding of the 4th World Congress on Intelligent Control and Automation.2002, June.10-14
[47]Yanqin Tian, Ping Guo, Michael R. Lyu. Comparative Studies on Feature Extraction Methods for Multispectral Remote Sensing Image Classification, Bei Jing, September 2009
[48]张克军.遥感图像特征提取方法研究.西北工业大学.2007,3.6-15
[49]杨玉静,冯建辉.纹理特征提取及辅助遥感影像分类技术研究.海洋测绘.2008,7,28(4).37-39
[50]骆玉霞,陈焕伟.遥感图像的特征提取与选择研究.研究与开发.2002,3(2).22
[51]赵鲁燕,尹君.图像融合效果评价方法研究.遥感信息.2005,4.16-17
[52]翟军涛,那彦.基于NSCT的多光谱和全色图像的融合.激光与红外.2008,3,38(3).282-284
[53]王海晖,彭嘉雄,吴巍,李峰.多源遥感图像融合效果评价方法研究.计算机工程与应用.2003,25.33-36
[2]杜凤兰,田庆久,夏学齐.遥感图像分类方法评析与展望.遥感技术与应用.2004.12,19(6).521-523
[3]Qian yin, Ping guo. Multispectral remote sensing image classification with multiple features. Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, Hong Kong,19-22 August 2007
[4]王一达,沈熙玲,谢炯.遥感图像分类方法综述.遥感信息.2006,5,68-69
[5]Jon Atli Benediktsson, Ioannis Kanellopoulos. Classification of Multisource and Hyperspectral Data Based on Decision Fusion. IEEE transactions on geoscience and remote sensing.1999.3,37(3)
[6]那彦.基于多分辨分析理论的图像融合方法.西安电子科技大学出版社.2007,5.135-157
[7]张文君.基于特征库和模糊技术的遥感图像分类研究.电子科技大学.2007.5，3-7
[8]Wen-jie Wang, Zhong-ming Zhao, Hai-qing Zhu. Object-oriented Multi-feature Fusion Change Detection Method for High Resolution Remote Sensing Image, 2009 Urban Remote Sensing Joint Event.IEEE,2009
[9]曾建航,魏萌,王靳辉等.基于知识的遥感影像模糊分类方法.测绘科学技术学报.2008,6,25(3).172-173
[10]郑孝勇,姚景顺,黄小毛等.基于D-S推理的模糊模式识别方法.系统工程与电子技术.2003,25(4).422-424
[11]刘安斐,李弼程,张先飞.基于数据融合的多特征遥感图像分类.数据采集与处理.2006,12,21(4).465-466
[12]胡文元,聂倩,黄小川.基于纹理和光谱信息的高分辨率遥感影像分类.测绘信息与工程.2009,34(1).16-17
[13]Ketut Wikantika, Wihartini, Ryutaro Tateishi. Spectral and Textural Information of Multisensor Data for Land Use Classification in Metropolitan Area, Japan,2000
[14]袁礼海,宋建社,薛文通等.利用灰度和纹理特征的SAR图像分类研究.电光与控制.2007,8,14(4).58-62
[15]林剑,王润生,鲍光淑.基于空间模糊纹理光谱的多光谱遥感图像分类方法.中国图象图形学报.2006,2,11(2).186-191
[16]吴学军.城市TM遥感图像分类方法研究.广西师范大学.2007,4.6-10
[17]王惠明,史萍.纹理特征的提取方法.国传媒大学学报自然科学版.2006,3,13(1).49-51
[18]杨利民,胡龙华,罗铁良等.常用的几种遥感图像特征提取技术分析.中国高新技术企业.2009,112(1).131-132
[19]刘丽,匡纲要.图像纹理特征提取方法综述.中国图象图形学报.2009,4,14(4).625-626
[20]刘新华,舒宁.纹理特征在多光谱遥感影像分类中的应用.测绘信息与工程.2006,31(3).31-32
[21]赵波,孙即祥,张学庆等.一种基于数据融合的遥感目标识别算法.无线电工程.2004,34(12).32-35
[22]王晓东,王荣芝.傅立叶变换在图像处理中的应用.牡丹江师范学院学报.2003，3.22-23
[23]张若岚,刘劲松.图像信号的频域理解.数字电视与数字视频.2002,237(3).12-15
[24]王冲.基于融合技术的遥感图像分类方法研究.西安电子科技大学学报.2009,3.13-15
[25]谭湘莹,于秀兰,钱国蕙.一种大小窗口结合的SAR图像纹理特征分类方法.系统工程与电子技术.2000,22(4).15-17
[26]游代安,余旭初,王建荣.一种基于知识的遥感图像模糊分类算法.工程图学报.2001,115-117
[27]侯海苗,冀小平.基于灰度共生矩阵的纹理特征.长治学院学报.2008,10,25(5).31-32
[28]丁胜峰.基于模糊推理的多源图像融合研究.南京理工大学.2004
[29]崔宇红,倪国强,范宏深.基于模糊推理的纹理图像融合方法研究.光学技术.2005.1,31(1).130-132
[30]Yan Wang, MO Jamshidi. Fuzzy Logic Applied in Remote Sensing Image Classification.2004
[31]党宏社,韩崇昭,王立琦等.基于模糊推理原理的多传感器数据融合方法.仪器仪表学报.2004,8,25(4).528
[32]Fang-ju Wang. Fuzzy Supervised Classification of Remote Sensing Images. IEEE transactions on geoscience and remote sensing.1990.4,28(2)
[33]韩金舫,桑琳,储毅.模糊控制中隶属函数的构造策略.交通与计算机.2001，6.11-12
[34]许将军.高光谱遥感图像特征提取及分类研究.电子科技大学.2007,4.10-15
[35]Marie-Catherine Mouchot, Basel Solaiman, Alfonso Parra. Use of fuzzy logic for unsupervised classification of remotely sensed images.1994
[36]刘宏兵,郭红建,刘道华.一种基于模糊推理的因素权重确定方法.大学数学.2006,6,22(3).139-143
[37]孟艳平.基于相似度的信息权重模糊推理方法.北京师范大学学报(自然科版).2008,42(1).21-24
[38]王海江,陈瑾,徐卫忠.基于Matlab编程方法实现模糊推理及解模糊的方法研究.现代电子技术.2004,190(23).45-46
[39]Yindi Zhao, Liangpei Zhang, Pingxiang Li. Texture Feature Fusion for High Resolution Satellite Image Classification. Proceeding of the Computer Graphics. Imaging and Vision:New Trends.2005
[40]李项军,黄旭华.基于最大隶属度原则的多传感器身份融合.电光与控制.2007.4,14(2).21-23
[41]Jun-ping Zhang, Ye-Zhang,Bin ZOU, Ting-xian Zhou. Fusion Classification of Hyperspectral Image Based On Adaptive Subspace Decomposition. IEEE,2000
[42]刘旭拢,何春阳,潘耀忠等.遥感图像分类精度的点、群样本检验与评估.遥感学报.2006,5,10(3).367
[43]Vassilis Tsagaris, Vassilis Anastassopoulos, George A. Lampropoulos. Fusion of Hyperspectral Data Using Segmented PCT for Color Representation and Classification. IEEE transactions on geoscience and remote sensing, 2005.10,43(10)
[44]吴健平,杨星卫.遥感数据分类结果的精度分析.遥感技术与应用.1995.2,10(1).19-20
[45]陈万海,赵春晖,刘春红.超谱遥感图像的模糊最大似然分类研究.哈尔滨工程大学学报.2006,10,24(5).774
[46]Wenjie Chen, Lihua Dou, Jie Chen. A Target Recognition Method Based on Feature Level Data Fusion. Proceeding of the 4th World Congress on Intelligent Control and Automation.2002, June.10-14
[47]Yanqin Tian, Ping Guo, Michael R. Lyu. Comparative Studies on Feature Extraction Methods for Multispectral Remote Sensing Image Classification, Bei Jing, September 2009
[48]张克军.遥感图像特征提取方法研究.西北工业大学.2007,3.6-15
[49]杨玉静,冯建辉.纹理特征提取及辅助遥感影像分类技术研究.海洋测绘.2008,7,28(4).37-39
[50]骆玉霞,陈焕伟.遥感图像的特征提取与选择研究.研究与开发.2002,3(2).22
[51]赵鲁燕,尹君.图像融合效果评价方法研究.遥感信息.2005,4.16-17
[52]翟军涛,那彦.基于NSCT的多光谱和全色图像的融合.激光与红外.2008,3,38(3).282-284
[53]王海晖,彭嘉雄,吴巍,李峰.多源遥感图像融合效果评价方法研究.计算机工程与应用.2003,25.33-36