黄刚,刘先林

• 1:首都师范大学资源环境与旅游学院
• 2:北京四维远见信息技术有限公司
• 3:中国测绘科学研究院

摘要(Abstract)：

针对现有极化合成孔径雷达影像语义分割方法存在的缺点,且该方向深度学习研究较少的问题,该文以国产机载全极化MiniSAR系统为依托,首先,对极化合成孔径雷达原理和基于深度学习的极化合成孔径雷达影像语义分割方法进行了分析;其次,使用实验数据对该方法的分割精度进行了验证分析,单类分割最大像素精度达94.61%,全类均交并比达到86.83%,结果证明了该分割方法的可行性和准确性;最后,为进一步提高极化SAR影像语义分割精度,在样本制作、提升效率、矢量化等方面提出了建议。

关键词(KeyWords)： 深度学习;合成孔径雷达;语义分割;全极化;精度

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划项目(2018YFF0215303,2017YFB0503004);; 高分辨率对地观测系统专项(42-Y2-0A14-9001-17/18)

作者(Author): 黄刚,刘先林

DOI: 10.16251/j.cnki.1009-2307.2019.06.024

参考文献(References)：

• [1]OLIVER C,QUEGAN S.Understanding synthetic aperture radar images[M].Raleigh,UK:SciTech Publishing,2004:1-10.
• [2]黄国满,张继贤,赵争,等.机载干涉SAR测绘制图应用系统研究[J].测绘学报,2008,37(3):277-279.(HUANG Guoman,ZHANG Jixian,ZHAO Zheng,et al.Research on airborne SAR interferometry mapping system[J].Acta Geodaetica et Cartographica Sinica,2008,37(3):277-279.)
• [3]王云艳,何楚,涂峰,等.特征选择双层SVM的融合算法用于极化SAR图像分类[J].武汉大学学报(信息科学版),2015,40(9):1157-1162.(WANG Yunyan,HE Chu,TU Feng,et al.PolSAR image classification using feature fution algorithm based on feature selection and bilayer SVM[J].Geomatics and Infornation Science of Wuhan University,2015,40(9):1157-1162.)
• [4]SALEHI M,SAHEBI M R,MAGHSOUDI Y.Improving the accuracy of urban land cover classification using Radarsat-2 PolSAR data[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(4):1394-1401.
• [5]陈博,王爽,焦李成,等.贝叶斯集成框架下的极化SAR图像分类[J].西安电子科技大学学报(自然科学版),2015,42(2):45-51.(CHEN Bo,WANG Shuang,JIAO Licheng,et al.Polarimetric SAR image classification via naive Bayes combination[J].Journal of Xidian University,2015,42(2):45-51.)
• [6]GOMEZ L,ALVAREZ L,MAZORRA L,et al.Fully PolSAR image classification using machine learning techniques and reaction-diffusion systems[J].Neurocomputing,2017,255:52-60.
• [7]SONG W Y,LI M,ZHANG P,et al.Unsupervised PolSAR image classification and segmentation using Dirichlet process mixture model and Markov random fields with similarity measure[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing(J-STARS),2017,10(8):3556-3568.
• [8]KRINIDIS S,CHATZIS V.A robust fuzzy local information C-Means clustering algorithm[J].IEEE Transactions on Image Processing,2010,19(5):1328.
• [9]CARVALHO E A,USHIZIMA D M,MEDEIROS F NS,et al.SAR imagery segmentation by statistical region growing and hierarchical merging[J].Digital Signal Processing,2010,20(5):1365-1378.
• [10]张倩,张荣,刘政凯.基于相似性度量的高分辨率SAR图像无监督分割[J].中国科学技术大学学报,2010,40(2):123-128.(ZHANG Qian,ZHANG Rong,LIUZhengkai.Unsupervised segmentation for high resolution SAR images based on homogeneity criterion[J].Journal of University of Science and Technology of China,2010,40(2):123-128.)
• [11]BOVIK A C.On detecting edges in speckle imagery[J].IEEE Transactions on Acoustics Speech&Signal Processing,1988,36(10):1618-1627.
• [12]MA X L,LIU S Q,HU S H,et al.SAR image edge detection via sparse representation[J].Soft Computing,2018,22(8):2507-2515.
• [13]WEISENSEEL R A,KARL W C,POWER G J.Markov random field segmentation methods for SAR target chips[J].Proceedings of SPIE:the International Society for Optical Engineering,1999,3721:462-473.
• [14]WANG F,WU Y,ZHANG Q,et al.Unsupervised SAR image segmentation using higher order neighborhood-based triplet Markov fields model[J].IEEETransactions on Geoscience&Remote Sensing,2014,52(8):5193-5205.
• [15]DUTTA A,SARMA K K.SAR image segmentation using wavelets and Gaussian mixture model[C]∥International Conference on Signal Processing and Integrated Networks.Piscataway:IEEE,2014:466-770.
• [16]万玲,尤红建,程跃兵,等.合成孔径雷达图像分割研究进展[J].遥感技术与应用,2018,33(1):10-24.(WAN Ling,YOU Hongjian,CHENG Yuebing,et al.Research progress of synthetic aperture radar image segmentation[J].Remote Sensing Technology and Application,2018,33(1):10-24.)
• [17]张椰,朱卫纲,邢强.SAR图像分割方法综述[J].兵器装备工程学报,2017,38(6):99-103.(ZHANG Ye,ZHU Weigang,XING Qiang.Overview of SAR image segmentation[J].Journal of Ordnance Equipment Engineering,2017,38(6):99-103.)
• [18]HINTON G E,OSINDERO S,TEH Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
• [19]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521:436-444.
• [20]HU F,XIA G S,HU J,et al.Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery[J].Remote Sensing,2015,7(11):14680-14707.
• [21]黄刚,刘力荣,史雪静,等.国产机载微型InSAR系统的DEM精度分析[J].测绘科学,2017,42(8):124-129.(HUANG Gang,LIU Lirong,SHI Xuejing,et al.Accuracy analysis of DEM based on domestic airborne mini-InSAR system[J].Science of Surveying and Mapping,2017,42(8):124-129.)
• [22]LEE J S,POTTIER E.Polarimetric radar imaging:from basics to applications[M].New York:CRSPress,2009:214-215.
• [23]CHEN L C,ZHU Y K,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[J/OL].[2019-02-28].https:∥arxiv.org/pdf/1802.02611.pdf.
• [24]GARCIA-GARCIA A,ORTS-ESCOLANO S,OPREAS O,et al.A review on deep learning techniques applied to semantic segmentation[J/OL].[2019-02-28].https:∥arxiv.org/pdf/1704.06857.pdf.