结合改进的降斑各向异性扩散和最大类间方差的SAR图像水体提取
|
摘要
利用遥感成像技术获取地面水体信息对水资源调查、自然灾害评估、流域规划和生态环境监测等具有重要意义,其中SAR成像作为大范围地面监测的可靠数据源,拥有全天时、全天候、广覆盖等光学遥感系统所不具有的优点,在水体提取中得到了广泛的应用。但由于受SAR图像相干斑噪声的影响,现有水体提取方法难以迅速、精确提取SAR图像中复杂精细的自然水体结构。为此,提出一种结合改进的降斑各向异性扩散和最大类间方差的SAR图像水体提取方法。首先,利用降斑各向异性扩散滤波SAR图像,在迭代滤波过程中通过计算图像间平均结构相似度自适应控制迭代过程,使其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,自适应确定阈值,实现滤波结果图像二值化分割。在二值化分割结果中,搜索具有相同像元值且位置相邻的前景像元点组成的连通区域,使每个单独的连通区域形成一个被标识的块,通过获取这些块的几何参数来消除图像的误分割,精确划定真实的水体区域,以实现SAR图像水体提取。为了验证提出方法的准确性,将本文方法提取的水体边界与人工绘制的水体边界叠加,结果表明二者可较好吻合。同时,从视觉、提取精度和运行时间对本文方法与目前常用3种SAR图像水体提取算法的结果进行比较分析,其中本文方法的运行时间满足实时应用的要求,提取结果的边界在2个像元评级区重叠度均达到80%,明显优于其他方法且本文方法提取结果在边界及细节信息等视觉方面也更加显著。对结果的定性及定量评价表明本文方法的优越性。
The use of remote sensing technology to obtain surface waterbody information is of great significance for water resource investigation, natural disaster assessment, watershed planning, and ecological environment monitoring. As a reliable data source for large-scale ground monitoring, SAR imaging has unique advantages that optical remote sensing systems of all-weather, all-weather, and wide coverage do not have, and has been widely used in waterbody mapping. However, due to the influence of speckle noise of SAR imagery, existing methods for waterbody mapping are difficult to extract the complex and fine natural water structures from SAR imagery quickly and accurately. In this paper, a new waterbody extraction method for SAR imagery based on improved speckle reducing anisotropic diffusion and maximum between-cluster variance was proposed. First, the SAR imagery were filtered by improved speckle reducing anisotropic diffusion. The iterative process was adaptively controlled by calculating the average structural similarity between imagery in the iterative filtering process, so that the fine edges and texture structure could be preserved simultaneously. Then, based on the criterion of maximum variance between classes, the threshold value was determined adaptively, and the binary segmentation of the filtered image was conducted. In the binarized segmentation result, connected foreground regions composed of the pixel points that have same intensity values and adjoin to each other spatially, are searched. In so doing, each connected region formed an identified block. By obtaining geometric parameters of these blocks, the false segmentation of the imagery was eliminated, and real waterbody areas were precisely identified based on the SAR imagery. To verify the accuracy of the proposed method, water boundaries extracted by this method were on manually drawn waterbody boundaries. Results of comparing the two methods show that they are pretty consistent with each other. Meanwhile, the results of our proposed method were compared with the results of three other kinds of water extraction algorithms commonly used for SAR imagery, in terms of the visual level, extraction accuracy, and running time. The running time of the proposed method meets the requirement of real-time application. The overlap degree of the extracted boundary in two pixels rating areas has reached 80%, which is obviously superior to other methods and the extraction results of the proposed method are also more significant in visual aspects such as boundary and detail information. The qualitative and quantitative evaluation shows the superiority of our proposed method.
The use of remote sensing technology to obtain surface waterbody information is of great significance for water resource investigation, natural disaster assessment, watershed planning, and ecological environment monitoring. As a reliable data source for large-scale ground monitoring, SAR imaging has unique advantages that optical remote sensing systems of all-weather, all-weather, and wide coverage do not have, and has been widely used in waterbody mapping. However, due to the influence of speckle noise of SAR imagery, existing methods for waterbody mapping are difficult to extract the complex and fine natural water structures from SAR imagery quickly and accurately. In this paper, a new waterbody extraction method for SAR imagery based on improved speckle reducing anisotropic diffusion and maximum between-cluster variance was proposed. First, the SAR imagery were filtered by improved speckle reducing anisotropic diffusion. The iterative process was adaptively controlled by calculating the average structural similarity between imagery in the iterative filtering process, so that the fine edges and texture structure could be preserved simultaneously. Then, based on the criterion of maximum variance between classes, the threshold value was determined adaptively, and the binary segmentation of the filtered image was conducted. In the binarized segmentation result, connected foreground regions composed of the pixel points that have same intensity values and adjoin to each other spatially, are searched. In so doing, each connected region formed an identified block. By obtaining geometric parameters of these blocks, the false segmentation of the imagery was eliminated, and real waterbody areas were precisely identified based on the SAR imagery. To verify the accuracy of the proposed method, water boundaries extracted by this method were on manually drawn waterbody boundaries. Results of comparing the two methods show that they are pretty consistent with each other. Meanwhile, the results of our proposed method were compared with the results of three other kinds of water extraction algorithms commonly used for SAR imagery, in terms of the visual level, extraction accuracy, and running time. The running time of the proposed method meets the requirement of real-time application. The overlap degree of the extracted boundary in two pixels rating areas has reached 80%, which is obviously superior to other methods and the extraction results of the proposed method are also more significant in visual aspects such as boundary and detail information. The qualitative and quantitative evaluation shows the superiority of our proposed method.
引文
[1] Kaplan G, Avdan U. Object-based water body extraction model using Sentinel-2 satellite imagery[J]. European Journal of Remote Sensing, 2017,50(1):137-143.
[2]饶萍,王建力.最优分区与最优指数联合的水体信息提取[J].地球信息科学学报,2017,19(5):702-712.[Rao P,Wang J L. Water extraction based on the optimal subregion and the optimal indexes combined[J]. Journal of Geo-information Science, 2017,19(5):702-712.]
[3]崔建楠,邢立新,叶超,等.双极化SAR影像的分类研究[J].安徽农业科学,2015(4):356-359.[Cui J N, Xing L X, Ye C,et al. Classification of dual-polarization SAR images[J].Journal of Anhui Agricultural Sciences, 2015(4):356-359.]
[4]赵伶俐,杨杰,李平湘,等.极化SAR影像弱散射地物统计分类[J].遥感学报,2013,17(2):312-319.[Zhao L L, Yang J, Li P X, et al. Statistical classification of weak backscattering scatterers of PolSAR image[J]. Journal of Remote Sensing, 2013,17(2):312-319.]
[5]徐川,华凤,眭海刚,等.多尺度水平集SAR影像水体自动分割方法[J].武汉大学学报·信息科学版,2014,39(1):27-31.[Xu C, Hu F, Sui H G, et al. Automatic water segmentation method in SAR images using multi-scale level set[J]. Geomatics and Information Science of Wuhan University, 2014,39(1):27-31.]
[6]汤玲英,刘雯,杨东,等.基于面向对象方法的Sentinel-1A SAR在洪水监测中的应用[J].地球信息科学学报,2018,20(3):377-384.[Tang L Y, Liu W, Yang D, et al. Flooding monitoring application based on the object-oriented method and sentinel-1A SAR data[J]. Journal of Geo-Information Science, 2018,20(3):377-384.]
[7] Canny J. A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986(6):679-698.
[8] Touzi R, Lopes A, Bousquet P. A statistical and geometrical edge detector for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 1988,26(6):764-773.
[9]吴诗婳,吴一全,周建江,等.基于Shearlet变换和Krawtchouk矩不变量的河流SAR图像分割[J].应用科学报,2015,33(1):21-31.[Wu S H, Wu Y Q, Zhou J J et al. Segmentation of SAR image of rivers based on shearlet transform and krawtchouk moment invariants[J]. Journal of Applied Sciences, 2015,33(1):21-31.]
[10]吴一全,李海杰,宋昱.基于多特征和WSVM的SAR图像河流目标检测[J].系统工程与电子技术,2015,37(6):1288-1293.[Wu Y Q, Li H J, Song Y. Target detection algorithm for rivers in SAR images based on multi-features and WSVM[J]. Systems Engineering and Electronics,2015,37(6):1288-1293.]
[11]韩斌,吴一全.SAR图像河流分割的加权指数区域能量模型[J].测绘学报,2017,46(9):1174-1181.[Han B, Wu Y Q. Weighted exponential region energy model for river segmentation of SAR images[J]. Acta Geodaetica et Cartographica Sinica, 2017,46(9):1174-1181.]
[12]安成锦,陈曾平.基于Otsu和改进CV模型的SAR图像水域分割算法[J].信号处理,2011,27(2):221-225.[An C J, Chen Z P. SAR water segmentation based on Otsu and improved CV model[J]. Signal Processing, 2011,27(2):221-225.]
[13]安成锦,牛照东,李志军,等.典型Otsu算法阈值比较及其SAR图像水域分割性能分析[J].电子与信息学报,2010,32(9):2215-2219.[An C J, Niu Z D, Li Z J, et al. Otsu threshold comparison and SAR water segmentation result analysis[J]. Journal of Electronics&Information Technology, 2010,32(9):2215-2219.]
[14] Zeng C, Bird S, Luce J, et al. A natural-rule-based-connection(NRBC)method for river network extraction from high-reso-lution imagery[J]. Remote Sensing, 2015,7(10):14055-14078.
[15]孙亚勇,李小涛,杨锋杰,等.基于星载SAR数据的山区水体提取方法研究[J].中国水利水电科学研究院学报,2014,12(3):258-263.[Sun Y Y, Li X T, Yang F J, et al.Study on the mountain water extraction method of the space-borne SAR image[J]. Journal of China Institute of Water Resources and Hydropower Research, 2014,12(3):258-263.]
[16]王军战,张友静,鲍艳松. ASAR斑点噪声模型验证及噪声滤除效果评价[J].地球信息科学学报,2008,10(2):183-189.[Wang J Z, Zhang Y J, Bao Y S. Validation model of ASAR speckle noise and evaluation effect of speckle noise filtering[J]. Journal of Geo-information Science, 2008,10(2):183-189.]
[17]魏丹,赵新强.一种高分辨率SAR图像河流边界自动提取方法[J].计算机应用与软件,2015,32(11):213-216.[Wei D, Zhao X Q. An automatic extraction method for river boundaries in high resolution SAR image[J]. Computer Applications and Software, 2015,32(11):213-216.]
[18]张朝晖,潘春洪,马颂德.一种基于修正Frost核的SAR图像斑点噪声抑制方法[J].中国图象图形学报,2005,10(4):431-435.[Zhang Z H, Pan C H, Ma S D. SAR image despeckling based on modified frost filter[J]. Journal of Image and Graphics, 2005,10(4):431-435.]
[19] Xiang Z, Deng K, Fan H. A new SAR image denoising algorithm of fusing Kuan filters and edge extraction[J]. International Symposium on Lidar&Radar Mapping Technologies&Applications, 2011,8286(4):393-403.
[20] Duan L F, Wei C T, Wang J, et al. A new method of denoising by reserving edges for SAR image[J]. Applied Mechanics&Materials, 2013,291-294:2859-2862.
[21] Yu Y, Acton S T. Speckle reducing anisotropic diffusion[J]. IEEE Transactions on Image Processing, 2002,11(11):1260-1270.
[22] Sun Q, Hossack J A, Tang J, et al. Speckle reducing anisotropic diffusion for 3D ultrasound images[J]. Computerized Medical Imaging&Graphics, 2004,28(8):461-470.
[23] http://rs.ceode.ac.cn/satelliteintroduce/introRadarsats.jsp#RADARSAT-1.
[24] http://cloud.satimage.cn/data_intro.
[25] http://www.cresda.com/CN/sjfw/zxsj/index.shtml.
[26] Jiang Z M, Zhou Y M. Image quality assessment based on multi-scale structural similarity[J]. Packaging Engineering, 2016,33:125-133.
[27] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems Man&Cybernetics, 2007,9(1):62-66.
[28] Modava M, Akbarizadeh G. Coastline extraction from SAR images using spatial fuzzy clustering and the active contour method[J]. International Journal of Remote Sensing, 2017,38(2):355-370.
[2]饶萍,王建力.最优分区与最优指数联合的水体信息提取[J].地球信息科学学报,2017,19(5):702-712.[Rao P,Wang J L. Water extraction based on the optimal subregion and the optimal indexes combined[J]. Journal of Geo-information Science, 2017,19(5):702-712.]
[3]崔建楠,邢立新,叶超,等.双极化SAR影像的分类研究[J].安徽农业科学,2015(4):356-359.[Cui J N, Xing L X, Ye C,et al. Classification of dual-polarization SAR images[J].Journal of Anhui Agricultural Sciences, 2015(4):356-359.]
[4]赵伶俐,杨杰,李平湘,等.极化SAR影像弱散射地物统计分类[J].遥感学报,2013,17(2):312-319.[Zhao L L, Yang J, Li P X, et al. Statistical classification of weak backscattering scatterers of PolSAR image[J]. Journal of Remote Sensing, 2013,17(2):312-319.]
[5]徐川,华凤,眭海刚,等.多尺度水平集SAR影像水体自动分割方法[J].武汉大学学报·信息科学版,2014,39(1):27-31.[Xu C, Hu F, Sui H G, et al. Automatic water segmentation method in SAR images using multi-scale level set[J]. Geomatics and Information Science of Wuhan University, 2014,39(1):27-31.]
[6]汤玲英,刘雯,杨东,等.基于面向对象方法的Sentinel-1A SAR在洪水监测中的应用[J].地球信息科学学报,2018,20(3):377-384.[Tang L Y, Liu W, Yang D, et al. Flooding monitoring application based on the object-oriented method and sentinel-1A SAR data[J]. Journal of Geo-Information Science, 2018,20(3):377-384.]
[7] Canny J. A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986(6):679-698.
[8] Touzi R, Lopes A, Bousquet P. A statistical and geometrical edge detector for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 1988,26(6):764-773.
[9]吴诗婳,吴一全,周建江,等.基于Shearlet变换和Krawtchouk矩不变量的河流SAR图像分割[J].应用科学报,2015,33(1):21-31.[Wu S H, Wu Y Q, Zhou J J et al. Segmentation of SAR image of rivers based on shearlet transform and krawtchouk moment invariants[J]. Journal of Applied Sciences, 2015,33(1):21-31.]
[10]吴一全,李海杰,宋昱.基于多特征和WSVM的SAR图像河流目标检测[J].系统工程与电子技术,2015,37(6):1288-1293.[Wu Y Q, Li H J, Song Y. Target detection algorithm for rivers in SAR images based on multi-features and WSVM[J]. Systems Engineering and Electronics,2015,37(6):1288-1293.]
[11]韩斌,吴一全.SAR图像河流分割的加权指数区域能量模型[J].测绘学报,2017,46(9):1174-1181.[Han B, Wu Y Q. Weighted exponential region energy model for river segmentation of SAR images[J]. Acta Geodaetica et Cartographica Sinica, 2017,46(9):1174-1181.]
[12]安成锦,陈曾平.基于Otsu和改进CV模型的SAR图像水域分割算法[J].信号处理,2011,27(2):221-225.[An C J, Chen Z P. SAR water segmentation based on Otsu and improved CV model[J]. Signal Processing, 2011,27(2):221-225.]
[13]安成锦,牛照东,李志军,等.典型Otsu算法阈值比较及其SAR图像水域分割性能分析[J].电子与信息学报,2010,32(9):2215-2219.[An C J, Niu Z D, Li Z J, et al. Otsu threshold comparison and SAR water segmentation result analysis[J]. Journal of Electronics&Information Technology, 2010,32(9):2215-2219.]
[14] Zeng C, Bird S, Luce J, et al. A natural-rule-based-connection(NRBC)method for river network extraction from high-reso-lution imagery[J]. Remote Sensing, 2015,7(10):14055-14078.
[15]孙亚勇,李小涛,杨锋杰,等.基于星载SAR数据的山区水体提取方法研究[J].中国水利水电科学研究院学报,2014,12(3):258-263.[Sun Y Y, Li X T, Yang F J, et al.Study on the mountain water extraction method of the space-borne SAR image[J]. Journal of China Institute of Water Resources and Hydropower Research, 2014,12(3):258-263.]
[16]王军战,张友静,鲍艳松. ASAR斑点噪声模型验证及噪声滤除效果评价[J].地球信息科学学报,2008,10(2):183-189.[Wang J Z, Zhang Y J, Bao Y S. Validation model of ASAR speckle noise and evaluation effect of speckle noise filtering[J]. Journal of Geo-information Science, 2008,10(2):183-189.]
[17]魏丹,赵新强.一种高分辨率SAR图像河流边界自动提取方法[J].计算机应用与软件,2015,32(11):213-216.[Wei D, Zhao X Q. An automatic extraction method for river boundaries in high resolution SAR image[J]. Computer Applications and Software, 2015,32(11):213-216.]
[18]张朝晖,潘春洪,马颂德.一种基于修正Frost核的SAR图像斑点噪声抑制方法[J].中国图象图形学报,2005,10(4):431-435.[Zhang Z H, Pan C H, Ma S D. SAR image despeckling based on modified frost filter[J]. Journal of Image and Graphics, 2005,10(4):431-435.]
[19] Xiang Z, Deng K, Fan H. A new SAR image denoising algorithm of fusing Kuan filters and edge extraction[J]. International Symposium on Lidar&Radar Mapping Technologies&Applications, 2011,8286(4):393-403.
[20] Duan L F, Wei C T, Wang J, et al. A new method of denoising by reserving edges for SAR image[J]. Applied Mechanics&Materials, 2013,291-294:2859-2862.
[21] Yu Y, Acton S T. Speckle reducing anisotropic diffusion[J]. IEEE Transactions on Image Processing, 2002,11(11):1260-1270.
[22] Sun Q, Hossack J A, Tang J, et al. Speckle reducing anisotropic diffusion for 3D ultrasound images[J]. Computerized Medical Imaging&Graphics, 2004,28(8):461-470.
[23] http://rs.ceode.ac.cn/satelliteintroduce/introRadarsats.jsp#RADARSAT-1.
[24] http://cloud.satimage.cn/data_intro.
[25] http://www.cresda.com/CN/sjfw/zxsj/index.shtml.
[26] Jiang Z M, Zhou Y M. Image quality assessment based on multi-scale structural similarity[J]. Packaging Engineering, 2016,33:125-133.
[27] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems Man&Cybernetics, 2007,9(1):62-66.
[28] Modava M, Akbarizadeh G. Coastline extraction from SAR images using spatial fuzzy clustering and the active contour method[J]. International Journal of Remote Sensing, 2017,38(2):355-370.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |