基于双树复小波和灰度共生矩阵的遥感图像分割
|
摘要
图像分割作为图像智能化处理的重要发展方向,受到图像处理界的高度关注。遥感图像分割作为图像分割中一个重要应用,深受研究者的重视。由于遥感图像与其他类型图像相比,具有灰度级多、信息量大、边界模糊等特点,且存在“同物异谱”、“异物同谱”的现象,这些使得遥感图像分割难度较大。然而,随着对地观测卫星技术的不断成熟,所拍摄到的遥感图像其纹理信息越来越丰富,因此如何利用纹理信息对遥感图像进行分割成为当前国内外学者关注的问题之一,纹理特征的提取是该课题的基础。
借助对遥感图像的纹理分析,提取遥感图像的纹理特征,可以推进遥感图像解译的自动化。在遥感图像分割中,将纹理分析的方法与常规的分割方法相结合,有助于提高遥感图像的最终分割精度,从而可以更好地理解遥感图像,并从遥感数据中提取各种有用的专题信息。
本文在阅读大量文献的基础上,对基于纹理的遥感图像分割进行了研究,提出一种新的纹理特征提取方法,即:将双树复小波变换和灰度共生矩阵相结合描述遥感图像局部纹理特征。这种方法采用双树复小波高频模值子带Gamma分布与Lognormal分布参数组合特征、灰度共生矩阵特征组成的联合纹理特征作为遥感图像每一像素特征,然后通过K均值聚类完成遥感图像分割。实验结果表明,基于这种方法提取的纹理特征用到遥感图像分割中,得到了较高的分割精度。
As an important development direction of image intelligent processing, image segmentation gets high attention in image processing domain. Remote sensing image segmentation, as one branch of image segmentation, obtains researchers’attention deeply. Compared with other types of images, remote sensing image has more gray levels, large information, fuzzy border, as well as‘same object different spectrum’and‘different object same spectrum’. Because of these characteristics, remote sensing image segmentation is too hard. However, as the earth observation satellite technology continues to mature, texture information of the remote sensing image is more and more abundant. How to use texture information in remote sensing image segmentation currently becomes one of the problems which the scholars pay close attention to. Texture feature extraction is the basis of this project.
Using in remote sensing image texture analysis and texture characteristics extraction, it can advance the automation of remote sensing image interpretation. In remote sensing image segmentation, it helps to improve the final remote sensing image segmentation through the texture analysis method combined with conventional segmentation method. It also can understand the remote sensing image better and extract all kinds of useful information from the remote sensing image data.
In this paper, based on the extensive literature on the remote sensing image segmentation techniques are studied, we propose a method to describe remote sensing image texture features based on Dual-Tree Complex Wavelet Transform (DT-CWT) and Gray-level Co-occurrence Matrix(GLCM). This method uses DT-CWT high-frequency sub-bands’Gamma and Lognormal parameters and features of GLCM as the feature vector of remote sensing image pixels. Then, use the K-means clustering to complete remote sensing image segmentation. The results of experiment prove that the feature based on this method can obtain more accurate remote sensing image segmentation results.
借助对遥感图像的纹理分析,提取遥感图像的纹理特征,可以推进遥感图像解译的自动化。在遥感图像分割中,将纹理分析的方法与常规的分割方法相结合,有助于提高遥感图像的最终分割精度,从而可以更好地理解遥感图像,并从遥感数据中提取各种有用的专题信息。
本文在阅读大量文献的基础上,对基于纹理的遥感图像分割进行了研究,提出一种新的纹理特征提取方法,即:将双树复小波变换和灰度共生矩阵相结合描述遥感图像局部纹理特征。这种方法采用双树复小波高频模值子带Gamma分布与Lognormal分布参数组合特征、灰度共生矩阵特征组成的联合纹理特征作为遥感图像每一像素特征,然后通过K均值聚类完成遥感图像分割。实验结果表明,基于这种方法提取的纹理特征用到遥感图像分割中,得到了较高的分割精度。
As an important development direction of image intelligent processing, image segmentation gets high attention in image processing domain. Remote sensing image segmentation, as one branch of image segmentation, obtains researchers’attention deeply. Compared with other types of images, remote sensing image has more gray levels, large information, fuzzy border, as well as‘same object different spectrum’and‘different object same spectrum’. Because of these characteristics, remote sensing image segmentation is too hard. However, as the earth observation satellite technology continues to mature, texture information of the remote sensing image is more and more abundant. How to use texture information in remote sensing image segmentation currently becomes one of the problems which the scholars pay close attention to. Texture feature extraction is the basis of this project.
Using in remote sensing image texture analysis and texture characteristics extraction, it can advance the automation of remote sensing image interpretation. In remote sensing image segmentation, it helps to improve the final remote sensing image segmentation through the texture analysis method combined with conventional segmentation method. It also can understand the remote sensing image better and extract all kinds of useful information from the remote sensing image data.
In this paper, based on the extensive literature on the remote sensing image segmentation techniques are studied, we propose a method to describe remote sensing image texture features based on Dual-Tree Complex Wavelet Transform (DT-CWT) and Gray-level Co-occurrence Matrix(GLCM). This method uses DT-CWT high-frequency sub-bands’Gamma and Lognormal parameters and features of GLCM as the feature vector of remote sensing image pixels. Then, use the K-means clustering to complete remote sensing image segmentation. The results of experiment prove that the feature based on this method can obtain more accurate remote sensing image segmentation results.
引文
[1]黄长专,王彪,杨忠.图像分割方法研究[J].计算机技术与发展.2009,19(6):76-79.
[2]刘建华,毛政元.高空间分辨率遥感影像分割方法研究综述[J].遥感信息,2009,6: 95-101.
[3]刘晓民.纹理研究及其应用综述[J].测控技术,2008,25(8): 2284-2288.
[4] Voorhees H, Poggio T. Detecting textons and texture boundaries in natural images [J]. Proceedings of the First International Conference on Computer Vision, London, 1987: 250-258.
[5] Tuceryan M, Jain A K. Texture Analysis//Chen C H, Pau L F, Wang P S. Handbook of Pattern Recognition and Computer Vision [J]. 2nd ed. Singapore: World Scientific Publishing Co., 1998:207-248.
[6] Cariou C, Chehdi K. Unsupervised texture segmentation using 2D AR modeling and stochastic version of EM procedure [J]. Patten Recognition Letters, 2008, 29(7):905-917.
[7] Haralick R M. Statistical and structured approaches to texture [J]. Proc of the IEEE, 1979, 67(5):786-808.
[8] Haralick R M, Shanmugam K, Dinstein I H. Textural features for image classification [J]. IEEE Trans. on SMC, 1973, 3(6):610-671.
[9] Srinivasa G N, Shobha G. Statistical texture analysis [J]. Proc. of World Academy of Science, Engineering and Technology, 2008, 36:1264-1270.
[10] Noda H et al. Texture image segmentation using MRF in wavelet domain [J]. Proc. of International Conference on Image processing.2000:572-575.
[11] Pentland P. Fractal-based descriptions of natural scenes [J]. IEEE PAMI. 1984, 6(6):661-674.
[12] Turner M R. Texture discrimination by Gabor functions [J]. Biological Cybernetics.1986, 55:71-82.
[13] Clark M, Bovik A C. Texture segmentation using Gabor modulation/demodulation [J]. Pattern Recognition Letters, 1987, 6:261-267.
[14] Semler L, Furst J. Wavelet-Based texture classification of tissues in computed tomography [J]. Pro. of the 18th IEEE Symposium on Computer Based Medical Systems.2005 :265-270.
[15]刘飞龙,陈云浩,李京.遥感影像纹理分析方法综述与展望[J].遥感技术与应用.2003,18(6):441-447.
[16]邱磊.基于内容的遥感图像挖掘方法研究(硕士论文).国防科学技术大学.2005,11.
[17]郑治真,沈萍,杨选辉等.小波变换及其MATLAB工具的应用[M].北京:地震出版社,2001:7-109.
[18]张涛.视频运动目标检测与跟踪算法的研究(博士论文).东南大学.2009,09.
[19]王芸.基于小波分析和神经网络的转子系统故障诊断方法研究(硕士论文).东北大学.2005,01.
[20] Kingsbury N G. The Dual-tree Complex Wavelet Transform: A New Technique for Shift Invariance and Directional Filters[C]//Proc. of the 8th IEEE DSP Workshop. Bryce Canyon, UT, USA: [s. n.], 1998:86-89.
[21] Selesnick I W, Baraniuk R G, Kingsbury N G. The Dual-tree Complex Wavelet Transform [J]. IEEE Signal Processing Magazine, 2005,22(6):123-151.
[22] Haralick R.M. , Shanmugam K., Dinstein I. Texture features for image classification [J]. IEEE Trans. System Man Cybernat.1973, 8(6):610-621.
[23]张强,王正林.精通MATLAB图像处理[M].北京:电子工业出版社,2009.
[24]冯建辉,杨玉静.基于灰度共生矩阵提取纹理特征图像的研究[J].北京测绘.2007(3):19-22.
[25]王琳娟,汪西莉.基于对偶树复小波变换的纹理特征提取及分割[J].计算机工程. 2008, 34(15):214-216.
[26] Baradi A, Parmiggian F. An Investigation of the Texture Characteristics Associated with Gray Level Co-occurrence Matrix Statistical Parameters [J]. IEEE Trans. on Geoscience and Remote Sensing, 1995, 33(2):293-303.
[27]王敏琴,韩国强,涂泳秋.新型的无监督纹理分割方法[J].电子科技大学学报,2010, 39(1):11-15.
[2]刘建华,毛政元.高空间分辨率遥感影像分割方法研究综述[J].遥感信息,2009,6: 95-101.
[3]刘晓民.纹理研究及其应用综述[J].测控技术,2008,25(8): 2284-2288.
[4] Voorhees H, Poggio T. Detecting textons and texture boundaries in natural images [J]. Proceedings of the First International Conference on Computer Vision, London, 1987: 250-258.
[5] Tuceryan M, Jain A K. Texture Analysis//Chen C H, Pau L F, Wang P S. Handbook of Pattern Recognition and Computer Vision [J]. 2nd ed. Singapore: World Scientific Publishing Co., 1998:207-248.
[6] Cariou C, Chehdi K. Unsupervised texture segmentation using 2D AR modeling and stochastic version of EM procedure [J]. Patten Recognition Letters, 2008, 29(7):905-917.
[7] Haralick R M. Statistical and structured approaches to texture [J]. Proc of the IEEE, 1979, 67(5):786-808.
[8] Haralick R M, Shanmugam K, Dinstein I H. Textural features for image classification [J]. IEEE Trans. on SMC, 1973, 3(6):610-671.
[9] Srinivasa G N, Shobha G. Statistical texture analysis [J]. Proc. of World Academy of Science, Engineering and Technology, 2008, 36:1264-1270.
[10] Noda H et al. Texture image segmentation using MRF in wavelet domain [J]. Proc. of International Conference on Image processing.2000:572-575.
[11] Pentland P. Fractal-based descriptions of natural scenes [J]. IEEE PAMI. 1984, 6(6):661-674.
[12] Turner M R. Texture discrimination by Gabor functions [J]. Biological Cybernetics.1986, 55:71-82.
[13] Clark M, Bovik A C. Texture segmentation using Gabor modulation/demodulation [J]. Pattern Recognition Letters, 1987, 6:261-267.
[14] Semler L, Furst J. Wavelet-Based texture classification of tissues in computed tomography [J]. Pro. of the 18th IEEE Symposium on Computer Based Medical Systems.2005 :265-270.
[15]刘飞龙,陈云浩,李京.遥感影像纹理分析方法综述与展望[J].遥感技术与应用.2003,18(6):441-447.
[16]邱磊.基于内容的遥感图像挖掘方法研究(硕士论文).国防科学技术大学.2005,11.
[17]郑治真,沈萍,杨选辉等.小波变换及其MATLAB工具的应用[M].北京:地震出版社,2001:7-109.
[18]张涛.视频运动目标检测与跟踪算法的研究(博士论文).东南大学.2009,09.
[19]王芸.基于小波分析和神经网络的转子系统故障诊断方法研究(硕士论文).东北大学.2005,01.
[20] Kingsbury N G. The Dual-tree Complex Wavelet Transform: A New Technique for Shift Invariance and Directional Filters[C]//Proc. of the 8th IEEE DSP Workshop. Bryce Canyon, UT, USA: [s. n.], 1998:86-89.
[21] Selesnick I W, Baraniuk R G, Kingsbury N G. The Dual-tree Complex Wavelet Transform [J]. IEEE Signal Processing Magazine, 2005,22(6):123-151.
[22] Haralick R.M. , Shanmugam K., Dinstein I. Texture features for image classification [J]. IEEE Trans. System Man Cybernat.1973, 8(6):610-621.
[23]张强,王正林.精通MATLAB图像处理[M].北京:电子工业出版社,2009.
[24]冯建辉,杨玉静.基于灰度共生矩阵提取纹理特征图像的研究[J].北京测绘.2007(3):19-22.
[25]王琳娟,汪西莉.基于对偶树复小波变换的纹理特征提取及分割[J].计算机工程. 2008, 34(15):214-216.
[26] Baradi A, Parmiggian F. An Investigation of the Texture Characteristics Associated with Gray Level Co-occurrence Matrix Statistical Parameters [J]. IEEE Trans. on Geoscience and Remote Sensing, 1995, 33(2):293-303.
[27]王敏琴,韩国强,涂泳秋.新型的无监督纹理分割方法[J].电子科技大学学报,2010, 39(1):11-15.