摘要
提出了一种可用于极化合成孔径雷达图像的海岸线提取方法。通过对极化SAR数据的分析,极化熵由于其对极化相关纹理敏感的特性而被选用来进行海陆之间的边缘检测与海岸线提取。针对极化熵图像,首先通过均值比率算子进行边缘图提取,包括边缘强度图和边缘方向图。在此基础上,提出了一种新的"coarse-fine"的海岸线提取方法。该方法包括两个步骤:首先利用边缘方向图,采用一种新的边缘跟踪的方法得到海岸线的粗检测轮廓;然后基于边缘强度图,在粗检测轮廓的基础上进行典型边缘点的提取,这些边缘点被称为控制点,最后利用控制点对粗检测轮廓进行修正,得到最终的海岸线。最后,基于Radarsat-2全极化数据进行了实验,实验结果证明,该方法可以很好的描绘出实验区域的海岸线,并优于其他对比方法。
This paper propose a new coastline extraction method for polarimetric SAR images.Through detailed analysis of the polarimetric SAR(PolSAR) data,this paper selects the polarimetric entropy as the basis of the edge detection and coastline extraction since it is sensitive to the polarization-dependent variation of texture.Firstly,the polarimetric entropy image is used to generate the edge maps including an edge intensity image and an edge orientation image.Based on the edge maps,a new "coarse-fine" method is proposed to extract the coastline.The latter is divided into three steps:first,a rough contour is extracted based on the edge orientation image;second,significant edge points,which are named control points,are extracted based on the edge intensity images,then correct the rough contour by using the control points and achieve the final coastline.The proposed method is used to extract the coastline on the Radarsat-2 quad-pol data and the results prove that the proposed method could better delineate the coastline than the comparative methods.
引文
[1]胡桂香,李宁,邢艳肖.基于KMM与超像素的SAR海面暗斑分割算法[J].国外电子测量技术,2016,35(6):101-108.
[2]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.
[3]朱贺,李臣明,张丽丽,等.联合灰度阈值分割及轮廓形态识别的河道提取[J].电子测量与仪器学报,2014,28(11):1288-1296.
[4]乔寅骐,肖健华,黄银和,等.基于改进RHT的SAR图像机场区域提取算法[J].电子测量技术,2016,39(2):56-60.
[5]BUONO A,NUNZIATA F,MASCOLO L,et al.A multipolarization analysis of coastline extraction using X-band COSMO-SkyMed SAR data[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(7):2811-2820.
[6]NUNZIATA F,MIGLIACCIO M,LI X F,et al.Coastline extraction using dual-polarimetric COSMOSkyMed pingpong mode SAR data[J].IEEE Geoscience&Remote Sensing Letters,2013,11(1):104-108.
[7]NUNZIATA F,BUONO A,MIGLIACCIO M,et al.Dual-polarimetric C-and X-band SAR data for coastline extraction[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2016,9(11):4921-4928.
[8]DING X,NUNZIATA F,LI X,et al.Performance analysis and validation of waterline extraction approaches using single-and dual-polarimetric SAR data[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2015,8(3):1019-1027.
[9]DENG Y,ZHANG H,WANG C,et al.Object-oriented water extraction of PolSAR image based on target decomposition[C].IEEE,Asia-Pacific Conference on Synthetic Aperture Radar,2015:596-601.
[10]CHUGH T J S,DUBEY R B,SUJATA.A new classification approach for PolSAR images[J].International Journal of Advanced Computer Research,2012,2(5):2333-2345.
[11]XIUSHAN L U,YAN Z.Application of improved ROA algorithm in SAR image edge detection[J].Journal of Shandong University of Science&Technology,2016(6):17-23.
[12]NASCIMENTO A D C,HORTA M M,FRERY A C,et al.Comparing edge detection methods based on stochastic entropies and distances for PolSAR imagery[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(2):648-663.
[13]WANG S,LIU K,PEI J,et al.Unsupervised classification of fully polarimetric SAR images based on scattering power entropy and copolarized ratio[J].IEEE Geoscience&Remote Sensing Letters,2013,10(3):622-626.
[14]ZHANG L,ZOU B,ZHANG J,et al.Classification of polarimetric SAR image based on support vector machine using multiple-component scattering model and texture features[J].EURASIP Journal on Advances in Signal Processing,2010(1):1-9.
[15]刘春,殷君君,杨健.基于混合边缘检测的极化SAR图像海岸线检测[J].系统工程与电子技术,2016,38(6):1262-1267.
[16]金长江,师廷伟.红外弱小目标检测背景抑制算法研究[J].中国测试,2016,42(4):115-119.
[17]ARMAROLI C,CIAVOLA P,PERINI L,et al.Critical storm thresholds for significant morphological changes and damage along the Emilia-Romagna coastline,Italy[J].Geomorphology,2012,143-144(2):34-51.
[18]CHENG D,MENG G,XIANG S,et al.Efficient sealand segmentation using seeds learning and edge directed graph cut[J].Neurocomputing,2016(207):36-47.
[19]闻新,张婉怡,王嘉轶,等.基于视觉感知的全参考图像质量评价算法[J].电子测量与仪器学报,2016,30(11):1780-1789
[20]HAGARA M,HLAVATOVIC A.Video segmentation based on Pratt's figure of merit[C].International Conference,2009:91-94.