基于特征提取的快速SAR-BM3D相干斑抑制算法
|
摘要
针对三维块匹配(BM3D)算法在合成孔径雷达(SAR)图像相干斑抑制时对图像块的相似性比较造成计算量过大的问题,提出一种基于特征提取的SAR-BM3D相干斑抑制算法。首先通过梯度奇异值分解对SAR图像的平坦区和边缘纹理特征区进行描述,从而获得SAR图像的结构信息,然后生成特征区域的相似集,最后根据得到的相似集来缩小同质区的搜索区域和扩大边缘纹理区的搜索区域,达到提高SAR-BM3D相似块匹配效率的目的。通过对比实验证明,算法能够有效加快SAR-BM3D运算时间,同时获得相干斑抑制效果较为良好的SAR图像。
Aimed at the shortage of the large amount computation for SAR image despeckling using Block-matching and3 Dtransform-domain collaborative(BM3 D)filter,a new SAR-BM3 Dimage despeckling method is proposed based on Singular value decomposition(SVD).Firstly,describe the flat area and edge texture area by SVD to gain SAR image structure information,and then from a similar set of feature regions,finally according to the obtained the similar set of feature reduce the search area of the homogeneous area and expand the search area of the edge texture area to improve SAR-BM3 Dsimilarity block matching efficiency.The experimental results show that the proposed algorithm can effectively speed up computation time and with well effect on SAR image despeckling.
Aimed at the shortage of the large amount computation for SAR image despeckling using Block-matching and3 Dtransform-domain collaborative(BM3 D)filter,a new SAR-BM3 Dimage despeckling method is proposed based on Singular value decomposition(SVD).Firstly,describe the flat area and edge texture area by SVD to gain SAR image structure information,and then from a similar set of feature regions,finally according to the obtained the similar set of feature reduce the search area of the homogeneous area and expand the search area of the edge texture area to improve SAR-BM3 Dsimilarity block matching efficiency.The experimental results show that the proposed algorithm can effectively speed up computation time and with well effect on SAR image despeckling.
引文
[1]OLIVER C,QUEGAN S.Understanding Synthetic Aperture Radar Images[M].Boston:Artech House,1998.
[2]MARTNEZ A,MARCHAND J L.SAR Image Quality Assessment[J].Revista de Teledeteccion,1993(2):1-7.
[3]刘佳.基于区域图和词袋模型的SAR图像分割[D].西安:西安电子科技大学,2014.
[4]颜学颖.SAR图像相干斑抑制和分割方法研究[D].西安:西安电子科技大学,2013.
[5]刘红华.基于Curvelet变换的SAR图像相干斑抑制[D].西安:西安电子科技大学,2010.
[6]XIE H,PIERCE L E,ULABY F T.SAR speckle reduction using wavelet denoising and Markov random field modeling[J].IEEE Transactions on Geoscience&Remote Sensing,2002,40(10):2196-2212.
[7]DABOV K,FOI A,KATKOVNIK V,et al.Image denoising by sparse 3-d transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080.
[8]DANIELYAN A,KATKOVNIK V,EGIAZARIAN K.BM3Dframes and variational image deblurring[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2012,21(4):1715.
[9]COZZOLINO D,PARRILLI S,SCARPA G,et al.Fast adaptive nonlocal SAR despeckling[J].IEEE Geoscience&Remote Sensing Letters,2013,11(2):524-528.
[10]许光宇.非局部图像去噪方法及其应用研究[D].合肥:合肥工业大学,2013.
[11]FENG X G,MILANFAR P.Multiscale principal components analysis for image local orientation estimation[C].Conference Record of the Thirty-Sixth Asilomar Conference on Signals,Systems and Computers,IEEE,2003:478-482.
[12]GUO G,WANG H,BELL D,et al.KNN modelbased approach in classification[J].Lecture Notes in Computer Science,2003,2888:986-996.
[13]周乐意,余文涛,陈嘉宇,等.SAR图像球流形局部嵌入建模及其分类方法[J].信号处理,2013,29(9):1163-1168.
[14]GUNTURI S B,THEERTHALA S S,PATEL N K,et al.Prediction of skin sensitization potential using Doptimal design and GA-kNN classification methods[J].Sar&Qsar in Environmental Research,2010,21(3-4):305.
[15]RONG L I,WEI Y S,ZHI S Z.SVM-KNN classifier:A new method of improving the accuracy of SVM classifier[J].Acta Electronica Sinica,2002,30(5):745-748.
[16]林耀进,李进金,陈锦坤,等.融合邻域信息的k-近邻分类[J].智能系统学报,2014,9(2):240-243.
[17]蔡贺,张睿.k最近邻域分类算法分析与研究[J].甘肃科技,2012,28(18):15-16.
[18]王小攀,马丽,刘福江.一种基于线性邻域传播的加权K近邻算法[J].计算机工程,2013,39(7):288-292.
[19]DELEDALLE C A,DENIS L,TUPIN F.How to compare noisy patches?patch similarity beyond gaussian Noise[J].International Journal of Computer Vision,2012,99(1):86-102.
[20]BHUIYAN M I H,AHMAD M O,SWAMY M N S.Spatially adaptive wavelet-based method using the cauchy prior for denoising the SAR images[J].IEEE Transactions on Circuits&Systems for Video Technology,2007,17(4):500-507.
[21]ARGENTI F,ALPARONE L.Speckle removal from SAR images in the undecimated wavelet domain[J].IEEE Transactions on Geoscience&Remote Sensing,2002,40(11):2363-2374.
[22]BIANCHI T,ARGENTI F,ALPARONE L.Segmentation-based MAP despeckling of SAR images in the undecimated wavelet domain[J].IEEE Transactions on Geoscience&Remote Sensing,2008,46(9):2728-2742.
[23]张维坤,叶伟,李国靖,等.基于相关向量机的SAR图像飞机目标分类方法研究[J].电子测量技术,2017,40(1):151-154.
[24]李倩,朱磊,邵文权.SAR图像各向异性扩散滤波算法[J].国外电子测量技术,2016,35(2):59-64.
[25]赵泉华,高郡,李玉.基于区域划分的多特征纹理图像分割[J].仪器仪表学报,2015,36(11):2519-2530.
[26]叶明,唐敦兵.区域清晰度的小波变换图像融合算法研究[J].电子测量与仪器学报,2015,29(9):1328-1333.
[2]MARTNEZ A,MARCHAND J L.SAR Image Quality Assessment[J].Revista de Teledeteccion,1993(2):1-7.
[3]刘佳.基于区域图和词袋模型的SAR图像分割[D].西安:西安电子科技大学,2014.
[4]颜学颖.SAR图像相干斑抑制和分割方法研究[D].西安:西安电子科技大学,2013.
[5]刘红华.基于Curvelet变换的SAR图像相干斑抑制[D].西安:西安电子科技大学,2010.
[6]XIE H,PIERCE L E,ULABY F T.SAR speckle reduction using wavelet denoising and Markov random field modeling[J].IEEE Transactions on Geoscience&Remote Sensing,2002,40(10):2196-2212.
[7]DABOV K,FOI A,KATKOVNIK V,et al.Image denoising by sparse 3-d transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080.
[8]DANIELYAN A,KATKOVNIK V,EGIAZARIAN K.BM3Dframes and variational image deblurring[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2012,21(4):1715.
[9]COZZOLINO D,PARRILLI S,SCARPA G,et al.Fast adaptive nonlocal SAR despeckling[J].IEEE Geoscience&Remote Sensing Letters,2013,11(2):524-528.
[10]许光宇.非局部图像去噪方法及其应用研究[D].合肥:合肥工业大学,2013.
[11]FENG X G,MILANFAR P.Multiscale principal components analysis for image local orientation estimation[C].Conference Record of the Thirty-Sixth Asilomar Conference on Signals,Systems and Computers,IEEE,2003:478-482.
[12]GUO G,WANG H,BELL D,et al.KNN modelbased approach in classification[J].Lecture Notes in Computer Science,2003,2888:986-996.
[13]周乐意,余文涛,陈嘉宇,等.SAR图像球流形局部嵌入建模及其分类方法[J].信号处理,2013,29(9):1163-1168.
[14]GUNTURI S B,THEERTHALA S S,PATEL N K,et al.Prediction of skin sensitization potential using Doptimal design and GA-kNN classification methods[J].Sar&Qsar in Environmental Research,2010,21(3-4):305.
[15]RONG L I,WEI Y S,ZHI S Z.SVM-KNN classifier:A new method of improving the accuracy of SVM classifier[J].Acta Electronica Sinica,2002,30(5):745-748.
[16]林耀进,李进金,陈锦坤,等.融合邻域信息的k-近邻分类[J].智能系统学报,2014,9(2):240-243.
[17]蔡贺,张睿.k最近邻域分类算法分析与研究[J].甘肃科技,2012,28(18):15-16.
[18]王小攀,马丽,刘福江.一种基于线性邻域传播的加权K近邻算法[J].计算机工程,2013,39(7):288-292.
[19]DELEDALLE C A,DENIS L,TUPIN F.How to compare noisy patches?patch similarity beyond gaussian Noise[J].International Journal of Computer Vision,2012,99(1):86-102.
[20]BHUIYAN M I H,AHMAD M O,SWAMY M N S.Spatially adaptive wavelet-based method using the cauchy prior for denoising the SAR images[J].IEEE Transactions on Circuits&Systems for Video Technology,2007,17(4):500-507.
[21]ARGENTI F,ALPARONE L.Speckle removal from SAR images in the undecimated wavelet domain[J].IEEE Transactions on Geoscience&Remote Sensing,2002,40(11):2363-2374.
[22]BIANCHI T,ARGENTI F,ALPARONE L.Segmentation-based MAP despeckling of SAR images in the undecimated wavelet domain[J].IEEE Transactions on Geoscience&Remote Sensing,2008,46(9):2728-2742.
[23]张维坤,叶伟,李国靖,等.基于相关向量机的SAR图像飞机目标分类方法研究[J].电子测量技术,2017,40(1):151-154.
[24]李倩,朱磊,邵文权.SAR图像各向异性扩散滤波算法[J].国外电子测量技术,2016,35(2):59-64.
[25]赵泉华,高郡,李玉.基于区域划分的多特征纹理图像分割[J].仪器仪表学报,2015,36(11):2519-2530.
[26]叶明,唐敦兵.区域清晰度的小波变换图像融合算法研究[J].电子测量与仪器学报,2015,29(9):1328-1333.