基于降斑各向异性扩散的SAR图像海岸线提取
|
摘要
受SAR图像相干斑噪声的影响,传统基于阈值的SAR图像海岸线提取方法难以迅速、精确地提取结构复杂精细的海岸线。为此,提出一种结合降斑各向异性扩散和大津法的SAR图像海岸线提取方法。首先,利用降斑各向异性扩散方法对SAR图像进行滤波,使其在尽可能滤除掉相干斑噪声的同时保持精细边缘和纹理结构;然后,以类间方差最大为准则,自适应地确定阈值,实现滤波结果图像二值化分割。在分割结果中,利用连通域标定法标定图像域,去除误分割的连通域,得到准确的海陆分割结果,以实现精确的SAR图像海岸线提取。对具有不同特点的真实大尺度SAR图像的实验结果和定量评价结果表明本文方法可以高精度地提取出光滑、连续的海岸线,相较其它方法具有更强的实用性。
Current threshold-based approaches could not quickly and precisely extract complex coastlines from SAR images due to speckle noises of SAR images. This paper proposes an approach of speckle reducing anisotropic diffusion to extract coastlines from SAR images. Firstly, the SAR image needs to be filtered using speckle reducing anisotropic diffusion. The speckle noises are filtered out as more as possible while maintaining tiny edges and texture structure of the image. After that, the threshold for segmentation is determined adaptively based on the rule of maximum inter-class variance, and the binary segmentation of the filtered image is achieved. The segmentation result is further processed by calibrating the image domain and removing false segmentation. Finally, accurate landsea segmentation is obtained. The approach has been applied to real large-scale SAR images with different properties.Results indicate that the proposed approach can precisely extract smooth and continuous coastlines and works better than other methods.
Current threshold-based approaches could not quickly and precisely extract complex coastlines from SAR images due to speckle noises of SAR images. This paper proposes an approach of speckle reducing anisotropic diffusion to extract coastlines from SAR images. Firstly, the SAR image needs to be filtered using speckle reducing anisotropic diffusion. The speckle noises are filtered out as more as possible while maintaining tiny edges and texture structure of the image. After that, the threshold for segmentation is determined adaptively based on the rule of maximum inter-class variance, and the binary segmentation of the filtered image is achieved. The segmentation result is further processed by calibrating the image domain and removing false segmentation. Finally, accurate landsea segmentation is obtained. The approach has been applied to real large-scale SAR images with different properties.Results indicate that the proposed approach can precisely extract smooth and continuous coastlines and works better than other methods.
引文
[1]姜大伟,范剑超,黄凤荣.SAR图像海岸线检测的区域距离正则化几何主动轮廓模型[J].测绘学报,2016,45(9):1 096-1 103.
[2]欧阳越,种劲松.SAR图像海岸线检测算法综述[J].国土资源遥感,2006,18(2):1-3.
[3]Lee J,Jurkevich I.Coastline Detection and Tracing in SAR Images[J].IEEE Transactions on Geoscience and Remote Sensing,1990,28(4):662-668.
[4]Mason D,Davenport I.Accurate and Efficient Determination of the Shoreline in ERS-1 SARImages[J].IEEE Transactions on Geoscience and Remote Sensing,1996,34(5):1 243-1 253.
[5]Niedermeier A,Romaneessen E,Lehner S.Detection of Coastlines in SAR Images Using Wavelet Methods[J].IEEE Transactions on Geoscience and Remote Sensing,2000,38(5):2 270-2 281.
[6]Liu C,Yang J,Yin J,et al.Coastline Detection in SAR Images Using a Hierarchical Level Set Segmentation[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(11):4 908-4 920.
[7]Ryan T,Sementilli P,Yuen P,et al.Extraction of Shoreline Features by Neural Nets and Image Processing[J].Photogrammetric Engineering and Remote Sensing,1991,57(7):947-955.
[8]Sheng G,Yang W,Deng X,et al.Coastline Detection in Synthetic Aperture Radar(SAR)Images by Integrating Watershed Transformation and Controllable Gradient Vector Flow(GVF)Snake Model[J].IEEEJournal of Oceanic Engineering,2012,37(3):375-383.
[9]Liu X,Jia H,Cao L,et al.Superpixel-based Coastline Extraction in SAR Images with Speckle Noise Removal[C]//Geoscience and Remote Sensing Symposium(IGARSS),2016IEEE International.IEEE,2016:1 034-1 037.
[10]李智,曲长文,周强,等.基于SLIC超像素分割的SAR图像海陆分割算法[J].雷达科学与技术,2017,15(4):354-358.
[11]Descombes X,Moctezuma M,Ma?tre H,et al.Coastline Detection by a Markovian Segmentation on SARImages[J].Signal Processing,1996,55(1):123-132.
[12]Baselice F,Ferraioli G.Unsupervised Coastal Line Extraction from SAR Images[J].IEEE Geoscience and Remote Sensing Letters,2013,10(6):1 350-1 354.
[13]Gambini J,Mejail M,Jacobo-Berlles J,et al.Accuracy of Edge Detection Methods with Local Information in Speckled Imagery[J].Statistics and Computing,2008,18(1):15-26.
[14]赵泉华,胡广臣,李玉.基于G0分布的SAR图像水边线提取方法[J].地理科学,2017,37(7):1 120-1 126.
[15]欧阳越,种劲松.基于改进水平截集算法的SAR图像海岸线检测[J].遥感技术与应用,2004,19(6):456-460.
[16]Cao K,Fan J,Wang X,et al.Coastline Automatic Detection Based on High Resolution SAR Images[C]//Earth Observation and Remote Sensing Applications(EORSA),2016 4th International Workshop on.IEEE,2016:43-46.
[17]Liu C,Xiao Y,Yang J.A Coastline Detection Method in Polarimetric SAR Images Mixing the RegionBased and Edge-Based Active Contour Models[J].IEEETransactions on Geoscience and Remote Sensing,2017,55(7):3 735-3 747.
[18]Ouyang Y,Chong J,Wu Y.Two Coastline Detection Methods in Synthetic Aperture Radar Imagery Based on Level Set Algorithm[J].International Journal of Remote Sensing,2010,31(17-18):4 957-4 968.
[19]黄魁华,张军.局部统计活动轮廓模型的SAR图像海岸线检测[J].遥感学报,2011,15(4):737-749.
[20]Al Fugura A,Billa L,Pradhan B.Semi-Automated Procedures for Shoreline Extraction Using Single RADARSAT-1 SAR Image[J].Estuarine Coastal and Shelf Science,2011,95:395-400.
[21]Liu H,Jezek K.A Complete High-Resolution Coastline of Antarctica Extracted from Orthorectified Radarsat SAR Imagery[J].Photogrammetric Engineering&Remote Sensing,2004,70(5):605-616.
[22]Nunziata F,Migliaccio M,Li X,et al.Coastline Extraction Using Dual-Polarimetric COSMO-SkyMed PingPong Mode SAR Data[J].IEEE Geoscience and Remote Sensing Letters,2014,11(1):104-108.
[23]Nunziata F,Buono A,Migliaccio M,et al.DualPolarimetric C-and X-Band SAR Data for Coastline Extraction[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(11):4 921-4 928.
[24]Buono A,Nunziata F,Mascolo L,et al.AMultipolarization Analysis of Coastline Extraction Using X-Band COSMO-SkyMed SAR Data[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(7):2 811-2 820.
[25]Modava M,Akbarizadeh G.Coastline Extraction from SARImages Using Spatial Fuzzy Clustering and the Active Contour Method[J].International Journal of Remote Sensing,2017,38(2):355-370.
[26]Shu Y,Li J,Gomes G.Shoreline Extraction from RADARSAT-2 Intensity Imagery Using a Narrow Band Level Set Segmentation Approach[J].Marine Geodesy,2010,33(2-3):187-203.
[27]陈祥,孙俊,尹奎英,等.基于Otsu与海域统计特性的SAR图像海陆分割算法[J].数据采集与处理,2014,29(4):603-608.
[28]Otsu N.A Thresholding Selection Method from GrayLevel Histogram[J].IEEE Transactions on Systems Man&Cybernetics,1979,9(1):62-66.
[29]Grosdidier S,Valero S,Chanussot J,et al.River Network Detection on Simulated SwotImages Based on Curvilinear Denoising and Morphological Detection[C]//Geoscience and Remote Sensing Symposium.IEEE,2012:5 454-5 457.
[30]Yu Y,Acton S.Speckle reducing anisotropic diffusion[J].IEEE Transactions on Image Processing,2002,11(11):1 260-1 270.
[31]Perona P,Malik J.Scale-Space and Edge Detection Using Anisotropic Diffusion[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2002,12(7):629-639.
[32]Lee J.A Simple Speckle Smoothing Algorithm for Synthetic Aperture Radar Images[J].IEEE Transactions on Systems Man&Cybernetics,1983,SMC-13(1):85-89.
[2]欧阳越,种劲松.SAR图像海岸线检测算法综述[J].国土资源遥感,2006,18(2):1-3.
[3]Lee J,Jurkevich I.Coastline Detection and Tracing in SAR Images[J].IEEE Transactions on Geoscience and Remote Sensing,1990,28(4):662-668.
[4]Mason D,Davenport I.Accurate and Efficient Determination of the Shoreline in ERS-1 SARImages[J].IEEE Transactions on Geoscience and Remote Sensing,1996,34(5):1 243-1 253.
[5]Niedermeier A,Romaneessen E,Lehner S.Detection of Coastlines in SAR Images Using Wavelet Methods[J].IEEE Transactions on Geoscience and Remote Sensing,2000,38(5):2 270-2 281.
[6]Liu C,Yang J,Yin J,et al.Coastline Detection in SAR Images Using a Hierarchical Level Set Segmentation[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(11):4 908-4 920.
[7]Ryan T,Sementilli P,Yuen P,et al.Extraction of Shoreline Features by Neural Nets and Image Processing[J].Photogrammetric Engineering and Remote Sensing,1991,57(7):947-955.
[8]Sheng G,Yang W,Deng X,et al.Coastline Detection in Synthetic Aperture Radar(SAR)Images by Integrating Watershed Transformation and Controllable Gradient Vector Flow(GVF)Snake Model[J].IEEEJournal of Oceanic Engineering,2012,37(3):375-383.
[9]Liu X,Jia H,Cao L,et al.Superpixel-based Coastline Extraction in SAR Images with Speckle Noise Removal[C]//Geoscience and Remote Sensing Symposium(IGARSS),2016IEEE International.IEEE,2016:1 034-1 037.
[10]李智,曲长文,周强,等.基于SLIC超像素分割的SAR图像海陆分割算法[J].雷达科学与技术,2017,15(4):354-358.
[11]Descombes X,Moctezuma M,Ma?tre H,et al.Coastline Detection by a Markovian Segmentation on SARImages[J].Signal Processing,1996,55(1):123-132.
[12]Baselice F,Ferraioli G.Unsupervised Coastal Line Extraction from SAR Images[J].IEEE Geoscience and Remote Sensing Letters,2013,10(6):1 350-1 354.
[13]Gambini J,Mejail M,Jacobo-Berlles J,et al.Accuracy of Edge Detection Methods with Local Information in Speckled Imagery[J].Statistics and Computing,2008,18(1):15-26.
[14]赵泉华,胡广臣,李玉.基于G0分布的SAR图像水边线提取方法[J].地理科学,2017,37(7):1 120-1 126.
[15]欧阳越,种劲松.基于改进水平截集算法的SAR图像海岸线检测[J].遥感技术与应用,2004,19(6):456-460.
[16]Cao K,Fan J,Wang X,et al.Coastline Automatic Detection Based on High Resolution SAR Images[C]//Earth Observation and Remote Sensing Applications(EORSA),2016 4th International Workshop on.IEEE,2016:43-46.
[17]Liu C,Xiao Y,Yang J.A Coastline Detection Method in Polarimetric SAR Images Mixing the RegionBased and Edge-Based Active Contour Models[J].IEEETransactions on Geoscience and Remote Sensing,2017,55(7):3 735-3 747.
[18]Ouyang Y,Chong J,Wu Y.Two Coastline Detection Methods in Synthetic Aperture Radar Imagery Based on Level Set Algorithm[J].International Journal of Remote Sensing,2010,31(17-18):4 957-4 968.
[19]黄魁华,张军.局部统计活动轮廓模型的SAR图像海岸线检测[J].遥感学报,2011,15(4):737-749.
[20]Al Fugura A,Billa L,Pradhan B.Semi-Automated Procedures for Shoreline Extraction Using Single RADARSAT-1 SAR Image[J].Estuarine Coastal and Shelf Science,2011,95:395-400.
[21]Liu H,Jezek K.A Complete High-Resolution Coastline of Antarctica Extracted from Orthorectified Radarsat SAR Imagery[J].Photogrammetric Engineering&Remote Sensing,2004,70(5):605-616.
[22]Nunziata F,Migliaccio M,Li X,et al.Coastline Extraction Using Dual-Polarimetric COSMO-SkyMed PingPong Mode SAR Data[J].IEEE Geoscience and Remote Sensing Letters,2014,11(1):104-108.
[23]Nunziata F,Buono A,Migliaccio M,et al.DualPolarimetric C-and X-Band SAR Data for Coastline Extraction[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(11):4 921-4 928.
[24]Buono A,Nunziata F,Mascolo L,et al.AMultipolarization Analysis of Coastline Extraction Using X-Band COSMO-SkyMed SAR Data[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(7):2 811-2 820.
[25]Modava M,Akbarizadeh G.Coastline Extraction from SARImages Using Spatial Fuzzy Clustering and the Active Contour Method[J].International Journal of Remote Sensing,2017,38(2):355-370.
[26]Shu Y,Li J,Gomes G.Shoreline Extraction from RADARSAT-2 Intensity Imagery Using a Narrow Band Level Set Segmentation Approach[J].Marine Geodesy,2010,33(2-3):187-203.
[27]陈祥,孙俊,尹奎英,等.基于Otsu与海域统计特性的SAR图像海陆分割算法[J].数据采集与处理,2014,29(4):603-608.
[28]Otsu N.A Thresholding Selection Method from GrayLevel Histogram[J].IEEE Transactions on Systems Man&Cybernetics,1979,9(1):62-66.
[29]Grosdidier S,Valero S,Chanussot J,et al.River Network Detection on Simulated SwotImages Based on Curvilinear Denoising and Morphological Detection[C]//Geoscience and Remote Sensing Symposium.IEEE,2012:5 454-5 457.
[30]Yu Y,Acton S.Speckle reducing anisotropic diffusion[J].IEEE Transactions on Image Processing,2002,11(11):1 260-1 270.
[31]Perona P,Malik J.Scale-Space and Edge Detection Using Anisotropic Diffusion[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2002,12(7):629-639.
[32]Lee J.A Simple Speckle Smoothing Algorithm for Synthetic Aperture Radar Images[J].IEEE Transactions on Systems Man&Cybernetics,1983,SMC-13(1):85-89.