基于瞬态系数的SAR图像分割方法研究
|
摘要
合成孔径雷达(SAR)具有全天时、全天候、高分辨率、成像技术灵活等特点,并且已经在军事和民用等领域获得广泛应用。SAR图像包含丰富的信息,通过数字图像分割技术可以从SAR图像中提取感兴趣区域或目标。图像分割是图像处理到图像分析的关键步骤,是实现特征提取、参数检测和模式识别等应用的基础,研究SAR图像分割技术具有很强的理论意义和实用价值。
目前,基于区域化模型的SAR图像分割方法成为研究的热点,它比基于阈值、基于边缘检测等分割方法具有更强的抑制噪声能力,并且分割结果更精确。区域模型的建立存在过度分割和边缘检测两个问题,针对这两个问题,本文以瞬态系数(ICOV)梯度算子为基础,提出建立边缘保持的SAR图像区域化模型,并应用于SAR图像分割。为此,主要开展以下研究内容:
1.研究建立具有边缘保持特性的SAR图像区域化模型。SAR图像的相干斑噪声会导致过度分割,并且破坏边缘信息。各向异性相干斑降噪(SRAD)滤波器不仅能有效滤除相干斑噪声以此减轻过度分割,而且具有保持边缘信息的能力,本文将SRAD应用到构建边缘保持特性的区域模型中。
2.提出将ICOV梯度与分水岭变换相结合获得区域化模型的初始区域。ICOV梯度算子对边缘具有单一峰值响应,并且响应宽度很窄;而分水岭对弱边缘具有良好响应,能检测出连续、封闭且单像素宽度的边缘。将ICOV与分水岭相结合,在获得大量均匀区域同时,还实现了目标边缘的准确检测。
3.研究构建基于分水岭初始区域的区域邻接图(RAG),完成SAR图像区域化模型的建立。传统的描述图像方式是基于像素水平的,数据量大而且图像结构复杂;而RAG以较小区域(即像素集)为基本单元描述图像上下文结构关系,简化了图像结构。
最后,将建立的SAR图像区域模型与区域水平马尔科夫场(MRF)分割方法相结合,并应用于SAR图像分割中。实验结果表明,本文提出的分割方法比基于其它经典梯度的分割方法具有更高的目标边缘检测与定位性能。
Synthetic aperture radar (SAR) can image in almost any condition and produce high-resolution images with good flexibility. SAR has been applied widely for military and civil use. People hope to extract the interesting regions by SAR image segmentation. Image segmentation plays a key role in digital image processing and works for characters extracting, paramerters measurement and pattern recognition. To study SAR image segmentation is meaningful to theories and applications.
Compared with traditional segmentation based histogram and edge detection, the methods region-based is a popular tool due to its ability of suppressing noise and more accurate segmentation. But the methods region-based has to resolve over-segmentation and regions edge location. According to these, instantaneous coefficient of variation (ICOV) gradient operator is used to construct a region model characterized by edge-preserving, and the main work is as follows:
1. To develop a SAR image region model characterized by edge-preserving. SAR image segmentation suffers from over segmentation and losing edge because of speckle. Speckle reducing anisotropic diffusion (SRAD) is an edge-preserving filter and used to reduce speckle and protect object edge in SAR images.
2. To propose a method to get initial regions using instantaneous coefficient of variation (ICOV) gradient operator and watershed transform. ICOV has single peak response and narrow respose width at edge location. Watershed transform is able to detect continous and close edge with one-pixel width. The properties of ICOV and watershed transform are advantageous to edge detection.
3. To construct region adjacency graph(RAG)based on initial regions of watershed transform. SAR image region model is accomplished by RAG. Traditional image is presentated based on pixels. RAG simplifies SAR image structures in the form of small regions (sets of pixels).
At the end, the above region model of SAR image is combined with region-level MRF to be used in SAR image segmentation. The experiments results prove that the proposed segmentation leads to more accurate edge detection compared to the segmentation based on other classical gradient operators.
目前,基于区域化模型的SAR图像分割方法成为研究的热点,它比基于阈值、基于边缘检测等分割方法具有更强的抑制噪声能力,并且分割结果更精确。区域模型的建立存在过度分割和边缘检测两个问题,针对这两个问题,本文以瞬态系数(ICOV)梯度算子为基础,提出建立边缘保持的SAR图像区域化模型,并应用于SAR图像分割。为此,主要开展以下研究内容:
1.研究建立具有边缘保持特性的SAR图像区域化模型。SAR图像的相干斑噪声会导致过度分割,并且破坏边缘信息。各向异性相干斑降噪(SRAD)滤波器不仅能有效滤除相干斑噪声以此减轻过度分割,而且具有保持边缘信息的能力,本文将SRAD应用到构建边缘保持特性的区域模型中。
2.提出将ICOV梯度与分水岭变换相结合获得区域化模型的初始区域。ICOV梯度算子对边缘具有单一峰值响应,并且响应宽度很窄;而分水岭对弱边缘具有良好响应,能检测出连续、封闭且单像素宽度的边缘。将ICOV与分水岭相结合,在获得大量均匀区域同时,还实现了目标边缘的准确检测。
3.研究构建基于分水岭初始区域的区域邻接图(RAG),完成SAR图像区域化模型的建立。传统的描述图像方式是基于像素水平的,数据量大而且图像结构复杂;而RAG以较小区域(即像素集)为基本单元描述图像上下文结构关系,简化了图像结构。
最后,将建立的SAR图像区域模型与区域水平马尔科夫场(MRF)分割方法相结合,并应用于SAR图像分割中。实验结果表明,本文提出的分割方法比基于其它经典梯度的分割方法具有更高的目标边缘检测与定位性能。
Synthetic aperture radar (SAR) can image in almost any condition and produce high-resolution images with good flexibility. SAR has been applied widely for military and civil use. People hope to extract the interesting regions by SAR image segmentation. Image segmentation plays a key role in digital image processing and works for characters extracting, paramerters measurement and pattern recognition. To study SAR image segmentation is meaningful to theories and applications.
Compared with traditional segmentation based histogram and edge detection, the methods region-based is a popular tool due to its ability of suppressing noise and more accurate segmentation. But the methods region-based has to resolve over-segmentation and regions edge location. According to these, instantaneous coefficient of variation (ICOV) gradient operator is used to construct a region model characterized by edge-preserving, and the main work is as follows:
1. To develop a SAR image region model characterized by edge-preserving. SAR image segmentation suffers from over segmentation and losing edge because of speckle. Speckle reducing anisotropic diffusion (SRAD) is an edge-preserving filter and used to reduce speckle and protect object edge in SAR images.
2. To propose a method to get initial regions using instantaneous coefficient of variation (ICOV) gradient operator and watershed transform. ICOV has single peak response and narrow respose width at edge location. Watershed transform is able to detect continous and close edge with one-pixel width. The properties of ICOV and watershed transform are advantageous to edge detection.
3. To construct region adjacency graph(RAG)based on initial regions of watershed transform. SAR image region model is accomplished by RAG. Traditional image is presentated based on pixels. RAG simplifies SAR image structures in the form of small regions (sets of pixels).
At the end, the above region model of SAR image is combined with region-level MRF to be used in SAR image segmentation. The experiments results prove that the proposed segmentation leads to more accurate edge detection compared to the segmentation based on other classical gradient operators.
引文
[1]宋建社,郑永安,袁礼海,合成孔径雷达图像理解与应用[M].北京:科学出版社,2008,1-2.
[2]焦李成等,智能SAR图像处理与解译[M].北京科学出版社,2008.
[3] Curlander,J.C.等著,韩传钊等译.合成孔径雷达:系统与信号处理[M].北京:电子工业出版社,2006.
[4] Bryant T. G., Morse G. B. Novak L M, et al. Tactical radars for ground surveillance[J]. The Lincoln Laboratory Journal, 2000,12(2):341-354.
[5]宋建社,袁礼海,薛文通. SAR图像处理的最新研究与应用[J].遥感技术与应用,2002,17(5):284-288.
[6]王正明,朱炬波等,SAR图像提高分辨率技术[M].北京:科学出版社,2006,56-95.
[7] Bovik A. C. On Detecting Edge in Speckle Imagery[J]. IEEE Trans. on Acoustic Speech and Signal Processing, 1988, 36 (10):1618-1627.
[8] D. Marr and E. Hildreth. Theory of edge detection[J]. Proc. Roy. Soc., 1980,B207 (1167):187–217.
[9]郑晓曦,严峻龙,图像分割新方法综述[J].计算机与数字工程, 2007,35(8):103-106.
[10] Vincent L. and Soille P. Watershed in digital spaces: an efficient algorithm based on immersion simulations[J]. IEEE Trans. Pattern Anal. Mach. Intell. 1991, 13(6): 583-598.
[11] Huawu Deng and David A. Clausi. Unsupervised Segmentation of Synthetic Aperture Radar Sea Ice Imagery Using MRF Models[J]. Proceedings of the First Canadian Conference on Computer and Robot Vision, 2004, 0-7695-2127.
[12] Huawu Deng, David A. Clausi. Unsupervised Image Segmentation Using A Simple MRF Model with A New Implementation Scheme[J]. Proceedings of the 17th International Conference on Pattern Recognition, 2004, 1051-4651/04.
[13] Huawu Deng and David A. Clausi,Gaussian MRF Rotation-Invariant Features for Image Classification[J] . IEEE Transaction on Pattern Analysys and Machine Intelligence, 2004, 26 (7):951-955.
[14] Q. Yu and D. A. Clausi. SAR sea-ice image analysis based on iterative region growing using semantics[J]. IEEE Trans. Geosci. Remote Sensing, 2007, 45(12): 3919-3931.
[15] Stan Z. Li. Markov random field modeling in image analysis [M]. New York: Springer, 2009:21-90.
[16] William K. Pratt. Digital Image Processing [M] .Wiley-Interscience, 4 Har/Cdr edition, 2007:590-593.
[17] Rafael C. Gonzales and Richard E. Woods.数字图像处理(第二版)[M].北京:电子工业出版社,2006: 568 - 595.
[18] Yu Q and Clausi D A. Filament preserving segmentation for SAR sea ice imagery using a new statistical model[J] . IEEE Trans. Geosci Remote Sensing, 2006,44 (12): 3678-3684.
[19] Soh L K and Tsatsoulis C. Unsupervised segmentation of ERS and RADARSAT sea ice images using multiresolution peak detection andaggregated population equalization [J]. Int. J. Remote Sensing, 1999, 20(15-16): 3087-3109.
[20]魏志成,周激流.一种新的图象分割自适应算法的研究[M].中国图象图形学报(A版),2000,5(3): 216 - 220.
[21]陈果,左洪福.图像的自适应模糊阈值分割法[J].自动化学报,2003,29(5):701 - 796.
[22] S. G. Mallat. A theory for multiresolution signal decomposition: the wavelet representation [J]. IEEE Trans. Pattern Anal. Machine Intell., 1989,11: 674-692.
[23] I. Daubechies. Ten Lectures on Wavelets [M]. 1992, SIAM, Philadelphia.
[24]胡召玲,郭达志,盛业华.基于小波纹理信息的星载SAR图像分类研究[J].遥感信息,2000,4:21-23
[25]薛笑荣,张艳宁,赵荣椿,段峰.基于小波变换的SAR图像分割[J].计算机工程,2004,30(7):11 - 12.
[26]曹兰英,夏正良,张昆辉.基于小波域MRF模型的SAR图象分割[J].东南大学学报,2004,34(6):847 - 850.
[27]张强,吴艳.基于上下文和隐类属的小波域马尔可夫随机场SAR图像分割[J]. 2008,30(1):211 - 215.
[28] YOKOYA N. LEVINE M D.Range image segmentation based on differential geometry: a hybrid approach[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 11(6):643-649.
[29] T. C. Pong, R. M. Haralick and L. G. Shapiro. Shape from shading using the Facet model Pattern Recognition[J], 1989,22(6): 683 - 695.
[30] R. M. Haralick. Zero crossing of second directional derivative edge operator. Proc. SPIE Symp. Robot Vision, 1982, 336: 91-99.
[31] Canny J. A computational approach to edge detection[J]. IEEE Trans Pattern Anal Machine Intell. , 1986,8:679-698.
[32]王小鹏,郝重阳,樊养余.基于形态学尺度空间和梯度修正的分水岭分割[J].电子与信息学报,2006,28(3):485 - 489.
[33]沃焱,韩国强,张见威.基于自适应预处理的图像分割方法[J]. 2007,29(1):87 - 91.
[34]刘海宾,何希勒,刘向东.基于分水岭和区域合并的图像分割算法[J].计算机应用研究,2007,24(9):307 - 308.
[35] S. Geman and D. Geman. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images [J] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 8:679-698.
[36] W. K. Pratt. Digital Image Processing[M]. New York: Wiley, 1977.
[37] Mohamed Airouche, Mimoun Zelmat and Madjid Kidouche[J]. Proceedings of ICCCC,2008, 144-149.
[38] Touzi R, Lop`es A and Bousquet P. A statistical and geometrical edge detector for SAR images . IEEE Trans Geosci Remote Sensing[J], 1988,26(6):764-773.
[39] C. J. Oliver, D. Blacknell, and R. G.White. Optimum edge detection in SAR[J]. IEEE Proc. Radar Sonar Navig., 1996, 143(1).
[40] Germain O and Réfrégier P. Edge localization in SAR images: Performance of the likelihood ratio filter and accuracy improvement with an active contour approach[J]. IEEE Trans. Image Processing , 2001, 10: 72– 78.
[41] C. J. Oliver, I. McConnell, D. Blacknell, and R. G. White. Optimal edge detection in SAR[J]. Proc. Int. Conf. Remote Sens., 1995, 2584:152–163.
[42] R. Fj?rtoft, P. Marthon, A. Lop`es, and E. CuberoCastan. Multiedge detection in SAR images[J]. inProc. ICASSP, 1997, 4: 2761-2764.
[43] R. Fjortoft, P. Marthon, A. Lopes and E. Cubero-Castan. Edge Detection in Radar Images Using Recursive Filters[J]. inProc. Second Asian Conference on Computer Vision, 1995, 3(5-8): 87-91.
[44] Fj?rtoft R, Lopes A, and Marthon P. An optimal multiedge detector for SAR image segmentation[J]. IEEE Trans. on Geoscience and Remote Sensing, 1998, 36(3): 793–802.
[45] A. Lopes, E. Nezry, R. Touzi, and H. Laur. Structure detection and statistical adaptive speckle filtering in SAR images[J]. Int. J. Remote Sens., 1993, 14:1735–1758.
[46] A. Baraldi and F. Parmiggiani. Arefined gamma MAP SAR speckle filter with improved geometrical adaptivity[J]. IEEE Trans. Geosci. Remote Sensing, 1994, 33:1245– 1257.
[47] E. P. Simoncelli and E. H. Adelson. Noise removal via Bayesian wavelet coring[J]. ICIP, 1996, 1: 379–382.
[48]朱家兵,陶亮,张卫佳,孙冬.基于小波变换的高分辨率SAR图像相干斑噪声抑制研究[J].雷达科学与技术,2005,3(5): 276 - 281.
[49] Y. Yue, M. Croitoru, A. Bidani, J. Zwischenberger, and J. Clark. Nonlinear multiscale wavelet di?usion for speckle suppression and edge enhancement in ultrasound images[J]. IEEE Trans. Medical Imaging, 2006, 25: 297–311.
[50] M. Chabert, J. Y. Tourneret, and Gilles Mesnager. Edge detection in speckled SAR images using the continuous wavelet transform[J]. inProc. IGARSS, Lincoln, Nebraska, 1996: 1842-1844.
[51] H.Xie, L.Pierce and F.T.Ulaby. SAR speckle reduction using wavelet denoising and markov random field modeling[J]. IEEE Trans. Geosci. Remote Sense, 2002, 40(10):2196-2212.
[52] J. S. Lee. Digital image enhancement and noise filtering by using local statistics[J]. IEEE Trans. Pattern Anal. Machine Intell., 1980, PAM1-2.
[53] J. S. Lee. Refined filtering of image noise using local statistics[J]. Comput. Graph. Image Process., 1982, 15: 380–389.
[54] J. S. Lee. Speckle suppression and analysis for synthetic aperture radar[J]. Opt. Eng., 1986, 25(5): 636–643.
[55] J. S. Lee and I. Jurkevich. Speckle filtering of synthetic aperture radar images: A review[J]. Remote Sensing Reviews, 1994, 8: 313-340.
[56] D. T. Kuan, A. A. Sawchuk, T. C. Strand, and P. Chavel. Adaptive restoration of images with speckle[J]. IEEE Trans. Acoust., Speech, Signal Processing, 1987, ASSP-35: 373–383.
[57] A. Lopes, R. Touzi, and E. Nezry. Adaptive speckle filters and scene heterogeneity[J]. IEEE Trans. Geosci. Remote Sensing , 1990, 28: 992–1000.
[58] A. Lopes, E. Nezry, R. Touzi, and H. Laur. Structure detection and statistical adaptive speckle filtering in SAR images[J]. Int. J. Remote Sensing, 1993, 14(9): 1735–1758.
[59] I. McConnell and C. Oliver. Comparison of Annealing and Iterated Filters for Speckle Reduction[J]. Europto Conference on SAR Image Analysis, Simulation and Modelling, Taormina, Italy, Proc. of SPIE, 1996, 2958:74-85.
[60] V. S. Frost, J. A. Stiles, K. S. Shanmugan, and J. C. Holtzman. A model for radar images and its application to adaptive digital filtering of multiplicativenoise[J]. IEEE Trans. Pattern Anal. Machine Intell., 1982,PAMI-4:157–166.
[61] J.S. Lee. A Simple Speckle Smoothing Algorithm for Synthetic Aperture Radar Images[J]. IEEE Trans. on Systems, Man and Cybernetics, 1983, SMC-13(1): 85-89.
[62] C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images[J]. Computer Vision, Sixth International Conference, 1998, 839-846
[63] Xie Jun,P. A. Heng. Color image diffusion using adaptive bilateral filter[J]. Engineering in Medicine and Biology Society,27th Annual International Conference,Shanghai,China,2005. 3433-3436.
[64] Zhang Buyue and J. P. Allebach. Adaptive bilateral filter for sharpness enhancement and noise removal[J]. Image Processing, IEEE Transactions, 2008, 17(5): 664-678.
[65] Zhang Ming and B. K. Gunturk. Multiresolution bilateral filtering for image denoising[J]. Image Processing, IEEE Transactions, 2008, 17(12):2324-2333.
[66] T. Iwai and T. Asakura. Speckle reduction in coherent information processing[J]. Proceedings of the IEEE , 1996, 84(5).
[67] M. R. Azimi-Sadjadi and S. Bannour. 2D adaptive block Kalman filtering of SAR imagery[J]. IEEE Trans. Geo science and Remote Sensing, 1991, 29: 742-753.
[68] S. J. Julier and J. K. Uhlmann. A General Method for Approximating Nonlinear Transformations of Probability Distributions . http://www.robots.ox.ac.uk/~siju, August 1994.
[69] S. J. Julier and J. K. Uhlmann. A new extension of the Kalman filter to nonlinear systems[J]. Proc. of AeroSense: The 11th Intnl. Symposium on Aerospace/ Defense Sensing, Simulation and Controls, Orlando, Florida, 1997.
[70] M. Dai, C. Peng, A. K. Chan, and D. Loguinov. Bayesian wavelet shrinkage with edge detection for SAR image despeckling[J]. IEEE Trans. Geoscience and Remote Sensing, 2004 , 42:1642-1648.
[71] A. Achim, E. E. Kuruoglu and J. Zerubia. SAR image filtering based on the heavy-tailed Rayleigh model[J]. IEEE Trans. Image Processing, 2006,15:2686 - 2693.
[72] G. R. K. S. Subrahmanyam, A. N. Rajagopalan, and R. Aravind. A Recursive Filter for Despeckling SAR Images[J]. IEEE Trans. Image Processing, 2008, 17(10): 1969-1974.
[73] F. Argenti, T. Bianchi and L. Alparone. Multiresolution MAP despeckling of SAR images based on locally adaptive generalized Gaussian pdf modeling[J]. IEEE Trans. Image Processing, 2006 , 15: 3385-3399.
[74] R. C. Hardie and C. G. Boncelet. IEEE Trans. on Sign. Proc, 1993.
[75] P. Perona and J. Malik. Scale-Space and Edge Detection Using Anisotropic Di?usion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7): 629-639.
[76] K. Z Abd-Elmonium, A. M. Youssef and Y. M. kadah. Real time speckle reduction and coherence enhancement in ultrasound imaging via nonlinear anisotropic diffusion[J]. IEEE Trans. Biomed.Engg., 2002, 49(9):997-1014.
[77]杨新.图像偏微分方程的原理与应用[M].上海:上海交通大学出版社,2003.
[78]张亶,陈刚.基于偏微分方程的图像处理[M].北京:高等教育出版社,2004.
[79]王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京:科学出版社,2008.
[80]廉晓丽,徐中宇,冯丽丽,晁玉忠.一种新的基于偏微分方程的图像修复[J].计算机工程,2009,35(6):234 - 236.
[81] Gilboa G, Zeevi Y Y and Sochen N A. Complex difiusion processes for image filtering[J]. In: Proceeding sof the 3rd International Conference on Scale-Space and Morphology in Computer Vision. London, UK: Springer-Verlag, 2001,299-307.
[82] Gilboa G, Sochen N A and Zeevi Y Y. Forward-and-backward difiusion processes for adaptive image enhancement and denoising[J]. IEEE Transactionson Image Processing, 2002, 11(7): 689 703.
[83]贾迪野,黄凤岗,苏菡.一种新的基于高阶非线性扩散的图像平滑方法[J].计算机学报, 2005,28(5): 882 - 891.
[84] A. Buades, B. Coll and J. M. Morel. Image denoising by non-local averaging[J]. Proc. IEEE Int’l Conf. Acoustics, Speech and Signal Processing, 2005,2: 25-28.
[85] A. Buades, B. Coll and J. M. Morel. A Non-Local Algorithm for Image Denoising[J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, 2: 60-65.
[86] Y. Yu and S. T. Acton. Speckle reducing anisotropic diffusion[J]. IEEE Trans Image Processing, 2002,11(11):1260-1270.
[87] Q. Yu and D. A. Clausi. IRGS: MRF based image segmentation using edge penalties and region growing[J]. IEEE Trans. Pattern Anal. Machine Intell., 2008,30(12): 2126-2139.
[88] Y. Yu and S. T. Acton. Edge Detection in Ultrasound Imagery Using the Instantaneous Coefficient of Variation[J]. IEEE Trans Image Processing, 2004, 13(12): 1640-1655.
[89] Qingling Sun, John A. Hossack, Jinshan Tang, and Scott T. Acton. Speckle reducing anisotropic diffusion for 3D ultrasound images[J]. Computerized Medical Imaging and Graphics, 2004, 28: 461–470.
[90] Rosenfield G H and Fitzpatrick-Lins K. A coefficient of agreement as a measure of thematic classification accuracy[J]. Photogrammetric Engineering & Remote Sensing, 1986, 52(2):223-227.
[91] http://marsais.nersc.no/synergy_wind_waves.html.
[92] S. T. Acton. Deconvolutional Speckle Reducing Anisotropic Diffusion[J]. ICIP 2005, 1:5-8.
[93] Yongjian Yu and Joseph Yadegar. Regularized Speckle Reducing Anisotropic Diffusion for Feature Characterization[J]. ICIP, 2006:1577-1580.
[94] S.Aja-fernandaz and C.alberola-lopez. On the estimation of coefficient of variation for anisotropic diffusion speckle filtering[J]. IEEE Trans. Image processing, 2005, 15(9): 2694-2701.
[95] Karl Krissian and Carl Fedrij. Oriented Speckle reducing anisotropic diffusion[J]. IEEE Trans. Image processing, 2007,15(5): 2694-2701.
[96] Walid Ibrahim and Mahmoud R. El-Sakka. Coefficient-Tracking Speckle Reducing Anisotropic Diffusion[J]. ICIAR, 2009, 136–145.
[2]焦李成等,智能SAR图像处理与解译[M].北京科学出版社,2008.
[3] Curlander,J.C.等著,韩传钊等译.合成孔径雷达:系统与信号处理[M].北京:电子工业出版社,2006.
[4] Bryant T. G., Morse G. B. Novak L M, et al. Tactical radars for ground surveillance[J]. The Lincoln Laboratory Journal, 2000,12(2):341-354.
[5]宋建社,袁礼海,薛文通. SAR图像处理的最新研究与应用[J].遥感技术与应用,2002,17(5):284-288.
[6]王正明,朱炬波等,SAR图像提高分辨率技术[M].北京:科学出版社,2006,56-95.
[7] Bovik A. C. On Detecting Edge in Speckle Imagery[J]. IEEE Trans. on Acoustic Speech and Signal Processing, 1988, 36 (10):1618-1627.
[8] D. Marr and E. Hildreth. Theory of edge detection[J]. Proc. Roy. Soc., 1980,B207 (1167):187–217.
[9]郑晓曦,严峻龙,图像分割新方法综述[J].计算机与数字工程, 2007,35(8):103-106.
[10] Vincent L. and Soille P. Watershed in digital spaces: an efficient algorithm based on immersion simulations[J]. IEEE Trans. Pattern Anal. Mach. Intell. 1991, 13(6): 583-598.
[11] Huawu Deng and David A. Clausi. Unsupervised Segmentation of Synthetic Aperture Radar Sea Ice Imagery Using MRF Models[J]. Proceedings of the First Canadian Conference on Computer and Robot Vision, 2004, 0-7695-2127.
[12] Huawu Deng, David A. Clausi. Unsupervised Image Segmentation Using A Simple MRF Model with A New Implementation Scheme[J]. Proceedings of the 17th International Conference on Pattern Recognition, 2004, 1051-4651/04.
[13] Huawu Deng and David A. Clausi,Gaussian MRF Rotation-Invariant Features for Image Classification[J] . IEEE Transaction on Pattern Analysys and Machine Intelligence, 2004, 26 (7):951-955.
[14] Q. Yu and D. A. Clausi. SAR sea-ice image analysis based on iterative region growing using semantics[J]. IEEE Trans. Geosci. Remote Sensing, 2007, 45(12): 3919-3931.
[15] Stan Z. Li. Markov random field modeling in image analysis [M]. New York: Springer, 2009:21-90.
[16] William K. Pratt. Digital Image Processing [M] .Wiley-Interscience, 4 Har/Cdr edition, 2007:590-593.
[17] Rafael C. Gonzales and Richard E. Woods.数字图像处理(第二版)[M].北京:电子工业出版社,2006: 568 - 595.
[18] Yu Q and Clausi D A. Filament preserving segmentation for SAR sea ice imagery using a new statistical model[J] . IEEE Trans. Geosci Remote Sensing, 2006,44 (12): 3678-3684.
[19] Soh L K and Tsatsoulis C. Unsupervised segmentation of ERS and RADARSAT sea ice images using multiresolution peak detection andaggregated population equalization [J]. Int. J. Remote Sensing, 1999, 20(15-16): 3087-3109.
[20]魏志成,周激流.一种新的图象分割自适应算法的研究[M].中国图象图形学报(A版),2000,5(3): 216 - 220.
[21]陈果,左洪福.图像的自适应模糊阈值分割法[J].自动化学报,2003,29(5):701 - 796.
[22] S. G. Mallat. A theory for multiresolution signal decomposition: the wavelet representation [J]. IEEE Trans. Pattern Anal. Machine Intell., 1989,11: 674-692.
[23] I. Daubechies. Ten Lectures on Wavelets [M]. 1992, SIAM, Philadelphia.
[24]胡召玲,郭达志,盛业华.基于小波纹理信息的星载SAR图像分类研究[J].遥感信息,2000,4:21-23
[25]薛笑荣,张艳宁,赵荣椿,段峰.基于小波变换的SAR图像分割[J].计算机工程,2004,30(7):11 - 12.
[26]曹兰英,夏正良,张昆辉.基于小波域MRF模型的SAR图象分割[J].东南大学学报,2004,34(6):847 - 850.
[27]张强,吴艳.基于上下文和隐类属的小波域马尔可夫随机场SAR图像分割[J]. 2008,30(1):211 - 215.
[28] YOKOYA N. LEVINE M D.Range image segmentation based on differential geometry: a hybrid approach[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 11(6):643-649.
[29] T. C. Pong, R. M. Haralick and L. G. Shapiro. Shape from shading using the Facet model Pattern Recognition[J], 1989,22(6): 683 - 695.
[30] R. M. Haralick. Zero crossing of second directional derivative edge operator. Proc. SPIE Symp. Robot Vision, 1982, 336: 91-99.
[31] Canny J. A computational approach to edge detection[J]. IEEE Trans Pattern Anal Machine Intell. , 1986,8:679-698.
[32]王小鹏,郝重阳,樊养余.基于形态学尺度空间和梯度修正的分水岭分割[J].电子与信息学报,2006,28(3):485 - 489.
[33]沃焱,韩国强,张见威.基于自适应预处理的图像分割方法[J]. 2007,29(1):87 - 91.
[34]刘海宾,何希勒,刘向东.基于分水岭和区域合并的图像分割算法[J].计算机应用研究,2007,24(9):307 - 308.
[35] S. Geman and D. Geman. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images [J] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 8:679-698.
[36] W. K. Pratt. Digital Image Processing[M]. New York: Wiley, 1977.
[37] Mohamed Airouche, Mimoun Zelmat and Madjid Kidouche[J]. Proceedings of ICCCC,2008, 144-149.
[38] Touzi R, Lop`es A and Bousquet P. A statistical and geometrical edge detector for SAR images . IEEE Trans Geosci Remote Sensing[J], 1988,26(6):764-773.
[39] C. J. Oliver, D. Blacknell, and R. G.White. Optimum edge detection in SAR[J]. IEEE Proc. Radar Sonar Navig., 1996, 143(1).
[40] Germain O and Réfrégier P. Edge localization in SAR images: Performance of the likelihood ratio filter and accuracy improvement with an active contour approach[J]. IEEE Trans. Image Processing , 2001, 10: 72– 78.
[41] C. J. Oliver, I. McConnell, D. Blacknell, and R. G. White. Optimal edge detection in SAR[J]. Proc. Int. Conf. Remote Sens., 1995, 2584:152–163.
[42] R. Fj?rtoft, P. Marthon, A. Lop`es, and E. CuberoCastan. Multiedge detection in SAR images[J]. inProc. ICASSP, 1997, 4: 2761-2764.
[43] R. Fjortoft, P. Marthon, A. Lopes and E. Cubero-Castan. Edge Detection in Radar Images Using Recursive Filters[J]. inProc. Second Asian Conference on Computer Vision, 1995, 3(5-8): 87-91.
[44] Fj?rtoft R, Lopes A, and Marthon P. An optimal multiedge detector for SAR image segmentation[J]. IEEE Trans. on Geoscience and Remote Sensing, 1998, 36(3): 793–802.
[45] A. Lopes, E. Nezry, R. Touzi, and H. Laur. Structure detection and statistical adaptive speckle filtering in SAR images[J]. Int. J. Remote Sens., 1993, 14:1735–1758.
[46] A. Baraldi and F. Parmiggiani. Arefined gamma MAP SAR speckle filter with improved geometrical adaptivity[J]. IEEE Trans. Geosci. Remote Sensing, 1994, 33:1245– 1257.
[47] E. P. Simoncelli and E. H. Adelson. Noise removal via Bayesian wavelet coring[J]. ICIP, 1996, 1: 379–382.
[48]朱家兵,陶亮,张卫佳,孙冬.基于小波变换的高分辨率SAR图像相干斑噪声抑制研究[J].雷达科学与技术,2005,3(5): 276 - 281.
[49] Y. Yue, M. Croitoru, A. Bidani, J. Zwischenberger, and J. Clark. Nonlinear multiscale wavelet di?usion for speckle suppression and edge enhancement in ultrasound images[J]. IEEE Trans. Medical Imaging, 2006, 25: 297–311.
[50] M. Chabert, J. Y. Tourneret, and Gilles Mesnager. Edge detection in speckled SAR images using the continuous wavelet transform[J]. inProc. IGARSS, Lincoln, Nebraska, 1996: 1842-1844.
[51] H.Xie, L.Pierce and F.T.Ulaby. SAR speckle reduction using wavelet denoising and markov random field modeling[J]. IEEE Trans. Geosci. Remote Sense, 2002, 40(10):2196-2212.
[52] J. S. Lee. Digital image enhancement and noise filtering by using local statistics[J]. IEEE Trans. Pattern Anal. Machine Intell., 1980, PAM1-2.
[53] J. S. Lee. Refined filtering of image noise using local statistics[J]. Comput. Graph. Image Process., 1982, 15: 380–389.
[54] J. S. Lee. Speckle suppression and analysis for synthetic aperture radar[J]. Opt. Eng., 1986, 25(5): 636–643.
[55] J. S. Lee and I. Jurkevich. Speckle filtering of synthetic aperture radar images: A review[J]. Remote Sensing Reviews, 1994, 8: 313-340.
[56] D. T. Kuan, A. A. Sawchuk, T. C. Strand, and P. Chavel. Adaptive restoration of images with speckle[J]. IEEE Trans. Acoust., Speech, Signal Processing, 1987, ASSP-35: 373–383.
[57] A. Lopes, R. Touzi, and E. Nezry. Adaptive speckle filters and scene heterogeneity[J]. IEEE Trans. Geosci. Remote Sensing , 1990, 28: 992–1000.
[58] A. Lopes, E. Nezry, R. Touzi, and H. Laur. Structure detection and statistical adaptive speckle filtering in SAR images[J]. Int. J. Remote Sensing, 1993, 14(9): 1735–1758.
[59] I. McConnell and C. Oliver. Comparison of Annealing and Iterated Filters for Speckle Reduction[J]. Europto Conference on SAR Image Analysis, Simulation and Modelling, Taormina, Italy, Proc. of SPIE, 1996, 2958:74-85.
[60] V. S. Frost, J. A. Stiles, K. S. Shanmugan, and J. C. Holtzman. A model for radar images and its application to adaptive digital filtering of multiplicativenoise[J]. IEEE Trans. Pattern Anal. Machine Intell., 1982,PAMI-4:157–166.
[61] J.S. Lee. A Simple Speckle Smoothing Algorithm for Synthetic Aperture Radar Images[J]. IEEE Trans. on Systems, Man and Cybernetics, 1983, SMC-13(1): 85-89.
[62] C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images[J]. Computer Vision, Sixth International Conference, 1998, 839-846
[63] Xie Jun,P. A. Heng. Color image diffusion using adaptive bilateral filter[J]. Engineering in Medicine and Biology Society,27th Annual International Conference,Shanghai,China,2005. 3433-3436.
[64] Zhang Buyue and J. P. Allebach. Adaptive bilateral filter for sharpness enhancement and noise removal[J]. Image Processing, IEEE Transactions, 2008, 17(5): 664-678.
[65] Zhang Ming and B. K. Gunturk. Multiresolution bilateral filtering for image denoising[J]. Image Processing, IEEE Transactions, 2008, 17(12):2324-2333.
[66] T. Iwai and T. Asakura. Speckle reduction in coherent information processing[J]. Proceedings of the IEEE , 1996, 84(5).
[67] M. R. Azimi-Sadjadi and S. Bannour. 2D adaptive block Kalman filtering of SAR imagery[J]. IEEE Trans. Geo science and Remote Sensing, 1991, 29: 742-753.
[68] S. J. Julier and J. K. Uhlmann. A General Method for Approximating Nonlinear Transformations of Probability Distributions . http://www.robots.ox.ac.uk/~siju, August 1994.
[69] S. J. Julier and J. K. Uhlmann. A new extension of the Kalman filter to nonlinear systems[J]. Proc. of AeroSense: The 11th Intnl. Symposium on Aerospace/ Defense Sensing, Simulation and Controls, Orlando, Florida, 1997.
[70] M. Dai, C. Peng, A. K. Chan, and D. Loguinov. Bayesian wavelet shrinkage with edge detection for SAR image despeckling[J]. IEEE Trans. Geoscience and Remote Sensing, 2004 , 42:1642-1648.
[71] A. Achim, E. E. Kuruoglu and J. Zerubia. SAR image filtering based on the heavy-tailed Rayleigh model[J]. IEEE Trans. Image Processing, 2006,15:2686 - 2693.
[72] G. R. K. S. Subrahmanyam, A. N. Rajagopalan, and R. Aravind. A Recursive Filter for Despeckling SAR Images[J]. IEEE Trans. Image Processing, 2008, 17(10): 1969-1974.
[73] F. Argenti, T. Bianchi and L. Alparone. Multiresolution MAP despeckling of SAR images based on locally adaptive generalized Gaussian pdf modeling[J]. IEEE Trans. Image Processing, 2006 , 15: 3385-3399.
[74] R. C. Hardie and C. G. Boncelet. IEEE Trans. on Sign. Proc, 1993.
[75] P. Perona and J. Malik. Scale-Space and Edge Detection Using Anisotropic Di?usion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7): 629-639.
[76] K. Z Abd-Elmonium, A. M. Youssef and Y. M. kadah. Real time speckle reduction and coherence enhancement in ultrasound imaging via nonlinear anisotropic diffusion[J]. IEEE Trans. Biomed.Engg., 2002, 49(9):997-1014.
[77]杨新.图像偏微分方程的原理与应用[M].上海:上海交通大学出版社,2003.
[78]张亶,陈刚.基于偏微分方程的图像处理[M].北京:高等教育出版社,2004.
[79]王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京:科学出版社,2008.
[80]廉晓丽,徐中宇,冯丽丽,晁玉忠.一种新的基于偏微分方程的图像修复[J].计算机工程,2009,35(6):234 - 236.
[81] Gilboa G, Zeevi Y Y and Sochen N A. Complex difiusion processes for image filtering[J]. In: Proceeding sof the 3rd International Conference on Scale-Space and Morphology in Computer Vision. London, UK: Springer-Verlag, 2001,299-307.
[82] Gilboa G, Sochen N A and Zeevi Y Y. Forward-and-backward difiusion processes for adaptive image enhancement and denoising[J]. IEEE Transactionson Image Processing, 2002, 11(7): 689 703.
[83]贾迪野,黄凤岗,苏菡.一种新的基于高阶非线性扩散的图像平滑方法[J].计算机学报, 2005,28(5): 882 - 891.
[84] A. Buades, B. Coll and J. M. Morel. Image denoising by non-local averaging[J]. Proc. IEEE Int’l Conf. Acoustics, Speech and Signal Processing, 2005,2: 25-28.
[85] A. Buades, B. Coll and J. M. Morel. A Non-Local Algorithm for Image Denoising[J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, 2: 60-65.
[86] Y. Yu and S. T. Acton. Speckle reducing anisotropic diffusion[J]. IEEE Trans Image Processing, 2002,11(11):1260-1270.
[87] Q. Yu and D. A. Clausi. IRGS: MRF based image segmentation using edge penalties and region growing[J]. IEEE Trans. Pattern Anal. Machine Intell., 2008,30(12): 2126-2139.
[88] Y. Yu and S. T. Acton. Edge Detection in Ultrasound Imagery Using the Instantaneous Coefficient of Variation[J]. IEEE Trans Image Processing, 2004, 13(12): 1640-1655.
[89] Qingling Sun, John A. Hossack, Jinshan Tang, and Scott T. Acton. Speckle reducing anisotropic diffusion for 3D ultrasound images[J]. Computerized Medical Imaging and Graphics, 2004, 28: 461–470.
[90] Rosenfield G H and Fitzpatrick-Lins K. A coefficient of agreement as a measure of thematic classification accuracy[J]. Photogrammetric Engineering & Remote Sensing, 1986, 52(2):223-227.
[91] http://marsais.nersc.no/synergy_wind_waves.html.
[92] S. T. Acton. Deconvolutional Speckle Reducing Anisotropic Diffusion[J]. ICIP 2005, 1:5-8.
[93] Yongjian Yu and Joseph Yadegar. Regularized Speckle Reducing Anisotropic Diffusion for Feature Characterization[J]. ICIP, 2006:1577-1580.
[94] S.Aja-fernandaz and C.alberola-lopez. On the estimation of coefficient of variation for anisotropic diffusion speckle filtering[J]. IEEE Trans. Image processing, 2005, 15(9): 2694-2701.
[95] Karl Krissian and Carl Fedrij. Oriented Speckle reducing anisotropic diffusion[J]. IEEE Trans. Image processing, 2007,15(5): 2694-2701.
[96] Walid Ibrahim and Mahmoud R. El-Sakka. Coefficient-Tracking Speckle Reducing Anisotropic Diffusion[J]. ICIAR, 2009, 136–145.