杨军,李波

• 1:兰州交通大学电子与信息工程学院
• 2:兰州交通大学测绘与地理信息学院甘肃省地理国情监测工程实验室

摘要(Abstract)：

针对传统迭代条件模式算法用于遥感影像分割时易出现误分割的问题,该文提出了结合核密度估计理论的迭代条件模式算法。使用自适应双边滤波器对影像进行预处理以提高影像质量,运用基于核密度估计理论的爬山算法获取影像的初始标记,结合MAP-MRF框架构建一种新的ICM算法对遥感影像进行分割。实验结果表明,使用基于核密度估计理论的爬山算法获取的初始标记后,基于MAP-MRF框架构建的分割算法能得到更准确的分割结果。和已有算法相比,该算法获得的分割结果在准确率和Kappa系数上都优于传统ICM算法、基于丰富语义的ICM算法和改进的ICM算法。

关键词(KeyWords)： 遥感影像;影像分割;迭代条件模式(ICM);自适应双边滤波器;核密度估计;MAP-MRF框架

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(61862039,61462059)

作者(Author): 杨军,李波

DOI: 10.16251/j.cnki.1009-2307.2020.05.010

参考文献(References)：

• [1]董志鹏，王密，李德仁．一种融合超像素与最小生成树的高分辨率遥感影像分割方法[J]．测绘学报，2017,46(6):734-742.(DONG Zhipeng,WANG Mi,LIDeren.A high resolution remote sensing image segmentation method by superpixels with minimum spanning tree[J].Acta Geodaetica et Cartographica Sinica,2017,46(6):734-742．）
• [2]马燕妮，明冬萍，杨海平．面向对象影像多尺度分割最大异质性参数估计[J]．遥感学报，2017,21(04):566-578.(MA Yanni,MING Dongping,YANG Haiping.Scale estimation of object-oriented image analysis based on spectral-spatial statistics[J].Journal of Remote Sensing,2017,21(4):566-578．）
• [3]BAO Huifang,ZHOU Linli,LIU Lei,et al.A MRF-based multi-agent system for remote sensing image segmentation[C]∥International Conference on Computing Intelligence and Information System.IEEEComputer Society,2017:246-249．
• [4]CHAUDHURI B,DEMIR B,CHAUDHURI S,et al.Multilabel remote sensing image retrieval using a semisupervised graph-theoretic method[J].IEEETransactions on Geoscience and Remote Sensing,2018,56(2):1144-1158．
• [5]FWU J K,DJURIC P.Unsupervised vector image segmentation by a tree structure-ICM algorithm[J].IEEE Transactions on Medical Imaging,1996,15(6):871-880．
• [6]DOULGERIS A P.An automatic u-distribution and Markov random field segmentation algorithm for PolSAR images[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(4):1819-1827．
• [7]LOBRY S,DENIS L,TUPIN F,et al.Double MRFfor water classification in SAR images by joint detection and reflectivity estimation[C]∥IGARSS2017-2017IEEE International Geoscience and Remote Sensing Symposium.[S.l.]:IEEE,2017:2283-2286．
• [8]ZHANG Yuhao,LU Pei,LIU Xiaoyun,et al.A modified MRF segmentation of brain MR images[C]∥International Congress on Image and Signal Processing,Biomedical Engineering and Informatics.[S.l.:s.n.],2017:1-5．
• [9]苏腾飞，张圣微，李洪玉．基于超像素MRF的农田地区高分遥感影像分割[J]．国土资源遥感，2018,30(1):37-44.(SU Tengfei,ZHANG Shengwei,LI Hongyu.High resolution remote sensing image segmentation using super-pixel MRF for agricultural area[J].Remote Sensing for Land and Resources,2018,30(1):37-44．）
• [10]ROTHER C,KOLMOGOROV V,BLAKE A．“Grabcut”-Interactive foreground extraction using iterated graph cuts[J].ACM Transactions on Graphics,2004,23(3):309-314．
• [11]TSO B C K,MATHER P M.Classification of multisource remote sensing imagery using a genetic algorithm and Markov random fields[J].IEEETransactions on Geoscience and Remote Sensing,1999,37(3):1255-1260．
• [12]BESAG J.On the statistical analysis of dirty pictures[J].Journal of the Royal Statistical Society,1986,48(3):259-302．
• [13]谢昭，谢年群，姚婷婷．一种图像空间下的ICM聚类方法[J]．电路与系统学报，2013,18(2):277-283.(XIE Zhao,XIE Nianqun,YAO Tingting.An ICMclustering method based on image space[J].Journal of Circuits and Systems,2013,18(2):277-283．）
• [14]SUBLIME J,CORNUéJOLS A,BENNANI Y.A new energy model for the hidden Markov random fields[J].2014,8835:60-67．
• [15]SUBLIME J,TROYA-GALVIS A,BENNANI Y,et al.Semantic rich ICM algorithm for VHR satellite images segmentation[C]∥IAPR International Conference on Machine Vision Applications.[S.l.]:IEEE,2015:45-48．
• [16]刘晓磊．基于MRF随机场模型的机器人视觉图像分割方法研究[D]．西安：西安建筑科技大学，2015:35-51.(LIU Xiaolei.Study on the method of robot visual segmentation based on MRF random field model[D].Xi’an:Xi’an University of Architecture and Technology,2015:35-51．）
• [17]杨军，裴剑杰．一种改进的ICM遥感影像分割算法[J]．国土资源遥感，2018,30(3):18-25.(YANG Jun,PEIJianjie.An improved ICM algorithm for remote sensing image segmentation[J].Remote Sensing for Land and Resources,2018,30(3):18-25．）
• [18]YOUSIF O,BAN Y.Improving SAR-Based urban change detection by combining MAP-MRF classifier and nonlocal means similarity weights[J].IEEEJournal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(10):4288-4300．
• [19]KALLEL I K,SOLAIMAN B.Contextual possibilistic modeling of pixellic knowledge for tumor segmentation in mammographic images[C]∥International Conference on Advanced Technologies for Signal and Image Processing.[S.l.]:IEEE,2017:1-6．
• [20]KHELIFI L,MIGNOTTE M.Semantic image segmentation using the ICM algorithm[C]∥IEEEInternational Conference on Image Processing.[S.l.]:IEEE,2018:3080-3084．
• [21]郭俊文，宋贵才．基于双边滤波的太赫兹图像去噪方法研究[J]．长春理工大学学报（自然科学版），2018,41(3):111-119.(GUO Junwen,SONG Guicai.Aterahertz image denoising algorithm based on adaptive bilateral filtering[J].Journal of Changchun University of Science and Technology(Natural Science Edition),2018,41(3):111-119．）
• [22]GEMAN S,GEMAN D.Stochastic relaxation,Gibbs distribution,and the Bayesian restoration of images[J].Pattern Analysis&Machine Intelligence,IEEETransaction on 1984,6(6):721-741．
• [23]SUDEEP P V,NIWAS S I,PALANISAMY P,et al.Enhancement and bias removal of optical coherence tomography images:An iterative approach with adaptive bilateral filtering[J].Computers in Biology&Medicine,2016,71(C):97-107．
• [24]PYATYKH S,HESSER J,ZHENG Lei.Image noise level estimation by principal component analysis[J].IEEE Transactions on Image Processing,2013,22(2):687-699．
• [25]曾接贤，付俊，符祥．特征点和不变矩结合的遥感图像飞机目标识别[J]．中国图象图形学报，2014,19(4):592-602.(ZENG Jiexian,FU Jun,FU Xiang.Aircraft target recognition in remote sensing images based on distribution of the feature points and invariant moments[J].Journal of Image and Graphics,2014,19(4):592-602.)