基于热核共生矩阵的SAR图像纹理目标识别 -- 西北工业大学学报,2016,34(2):356-361
论文:2016,Vol:34,Issue(2):356-361
引用本文:
杨中悦, 林伟, 延伟东, 温金环. 基于热核共生矩阵的SAR图像纹理目标识别[J]. 西北工业大学学报
Yang Zhongyue, Lin Wei, Yan Weidong, Wen Jinhuan. SAR Image Target Recognition Based on Heat Kernel Co-Occurrence Matrix[J]. Northwestern polytechnical university

基于热核共生矩阵的SAR图像纹理目标识别
杨中悦, 林伟, 延伟东, 温金环
西北工业大学 理学院数学系, 陕西 西安 710129
摘要:
相干斑噪声是合成孔径雷达(synthetic aperture radar,SAR)成像系统的固有缺陷,严重影响SAR图像的识别率。为此,提出了一种基于热核共生矩阵提取纹理特征统计量的算法,并将此方法用于SAR图像的纹理目标识别。首先通过构建图结构计算出图像每一点的热核特征,生成热核共生矩阵并计算纹理特征统计量;进而将热核特征与纹理特征统计量相结合构成特征矩阵;最后通过计算对应特征向量之间的相关系数,利用相似性度量的方法,实现SAR图像的纹理目标识别。实验结果表明,该方法可以识别SAR图像纹理目标,且识别效果要优于经典的基于灰度共生矩阵提取纹理统计量的方法。
关键词:    纹理目标    目标识别    热核特征    共生矩阵    特征向量   
SAR Image Target Recognition Based on Heat Kernel Co-Occurrence Matrix
Yang Zhongyue, Lin Wei, Yan Weidong, Wen Jinhuan
Department of Applied Mathematics, Northwestern Poly-technical University, Xi'an, 710129, China
Abstract:
Coherent spot noise is the inherent defect of SAR(Synthetic Aperture Radar), it seriously affect to the rate of SAR images recognition. In the process of SAR image recognition, we need select a characteristic without noise interference due to influence of the coherent spot. In this way, a novel method of extracting the texture feature was put forward and this feature was used in SAR image target recognition. Firstly, by building a graph structure, we computed the heat kernel feature at every point in SAR image. Furthermore, the heat kernel co-occurrence matrix was generated and its texture feature statistics were calculated; then we combined the heat kernel feature and texture feature statistics to form the characteristic matrix. Finally, we calculated the correlated coefficient of two SAR images and recognition was obtained by comparing similarities of the whole SAR images. This method, which is used to study the characteristics of heat kernel on graph, can allow full play to advantages of graph spectral theory. Experimental and their analysis show preliminarily that, compared with the method of classic gray co-occurrence matrix, this method, which is based on heat kernel co-occurrence matrix, shows higher recognition rate for SAR images.
Key words:    texture target    target recognition    heat kernel    co-occurrence matrix    feature vector   
收稿日期: 2015-10-09     修回日期:
DOI:
基金项目: 国家自然科学基金(61201323、61301196)与西北工业大学研究生创新创意种子基金(Z2015153)资助
通讯作者:     Email:
作者简介: 杨中悦(1991-),女,西北工业大学硕士研究生,主要从事遥感图像处理研究。
相关功能
PDF(2041KB) Free
打印本文
把本文推荐给朋友
作者相关文章
杨中悦  在本刊中的所有文章
林伟  在本刊中的所有文章
延伟东  在本刊中的所有文章
温金环  在本刊中的所有文章

参考文献:
[1] Singh J, Datou M. SAR Image Categorization With Log Cumulants of the Fractional Fourier Transform Coefficients[J]. IEEE Trans on Geoscience and Remote Sensing, 2013, 51(12):5273-5282
[2] Voisin A, Krylov V, Moser G, et al. Classification of Very High Resolution SAR Images of Urban Areas Using Copulas and Texture in a Hierarchical Markov Random Field Model[J]. IEEE Trans on Geoscience and Remote Sensing Letters, 2013, 10(1):96-100
[3] Gamba P, Massimilano A, Mattia S. Robust Extraction of Urban Area Extents in HR and VHR SAR Images[J]. Selected Topics in Appl Earth Observtions and Remote Sensing, 2011,4(1):27-34
[4] Akbarizadeh G. A New Statistical-Based Kurtosis Wavelet Energy Feature for Texture Recognition of SAR Images[J]. IEEE Trans on Geoscience and Remote Sensing, 2012,50(11):4358-4368
[5] Champion I, Germain C, Da Costa J P, et al. Retrieval of Forest Stand Age from SAR Image Texture for Varying Distance and Orientation Values of the Gray Level Co-Occurrence Matrix[J]. IEEE Trans on Geoscience and Remote Sensing, 2014,11(1):5-9
[6] Haralick R M, Shanmugam K, Dinstein I. Textural Features for Image Classification[J]. IEEE Trans on Systerms Manad Cybernetic, 1973, 6:610-621
[7] Qin H J, Hancock E R. Clustering and Embedding Using Commute Times[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(11):1873-1890
[8] Xiao B, Wilson R, Hancock E. Object Recognition Using Graph Spectral Invariants[C]//19th International Conference on Pattern Recognition, 2008:1-4
[9] Sun J, Ovsjanikov M, Guibas L. A Concise and Provably Informative Multi-Scale Signature Based on Heat Diffusion[C]//Computer Graphics Forum Blackwell Publishing Ltd, 2009:1383-1392
[10] 罗湾,林伟,温金环. 基于区域热核不变量的SAR图像变化检测[J]. 宇航学报,2011,32(11):2410-2416 Luo Wan, Lin Wei, Wen Jinhuan. Change Detection Based on Region Heat Kernel Invariants for SAR Image[J]. Journal of Astronautics, 2011, 32(11):2410-2416(in Chinese)
[11] 杨绪峰,林伟,温金环,等. 采用热核特征的SAR图像目标识别[J]. 红外与激光工程,2014,43(11):3795-3801 Yang Xufeng, Lin Wei, Wen Jinhuan, et al. SAR Image Target Recognition Based on Heat Kernel[J]. Infrared and Laser Engineering,2014,43(11):3795-3801(in Chinese)
[12] 王一丹,林伟,延伟东,等. 基于热核特征的SAR图像地物识别方法[J].系统工程与电子技术.2015,37(5):1047-1054 Wang Yidan, Lin Wei, Yan Weidong, et al. Methods of SAR Image Terrain Recognition Based on Heat Kernel Feature[J]. Systems Engineering and Electronics, 2015, 37(5):1047-1054(in Chinese)
[13] Zelnik-Manor L, Perona P. Self-Tuning Spectral Clustering[C]//Advances in Neural Information Processing Systems, 2004:1601-1608
[14] Bai X, Edwin H R, Richard W C. Geometric Characterization and Clustering of Graphs Using Heat Kernel Embedding[J]. Image and Vision Computing, 2010, 28:1003-1021