高分辨率遥感影像分割方法研究
|
摘要
在遥感应用分析中,遥感影像分割是低层影像处理和中高层影像分析和理解的桥梁,是实现遥感影像信息自动提取的关键步骤,具有重要的意义。随着大量高分辨率遥感影像的出现,传统基于像素的影像处理方法已不能适应高分辨率遥感影像。近年来,国内外研究者们提出了面向对象影像的分析方法,而面向对象影像分析方法的关键就是影像分割,影像分割精度直接影响着高分辨率遥感信息提取和目标识别的精度。首先给出一般图像分割方法的综述;然后分析和总结了当前主要的高分辨率遥感影像分割方法,着重阐述了均值漂移、分形网络进化、马尔科夫随机场等分割方法的特点和研究现状;最后,对高分辨率遥感应用分析中影像分割方法的发展趋势进行了讨论与展望。
In remote sensing application analysis,image segmentation is the bridge between low- level image processing and high-level image analysis and understanding. It is also the first step to realize automatic extraction from remote sensing images and is of great significance. As a large number of high resolution remote sensing images are obtained,traditional image segmentation methods are not meeting the rising demands of high resolution remote sensing image analysis. In recent years,object- based image analysis( OBIA) method is proposed by domestic and foreign researchers. The key of OBIA is image segmentation which directly influences the accuracy of high resolution remote sensing information extraction and target recognition. In this paper,a review of general image segmentation methods are firstly given,then remote sensing image segmentation methods which are widely used at present are summarized and analyzed. Characteristics and research status of methods such as Mean Shift algorithm,FNEA,MRF etc. are focused on. In the end,the development tendency of image segmentation in high resolution remote sensing application analysis is discussed and prospected.
In remote sensing application analysis,image segmentation is the bridge between low- level image processing and high-level image analysis and understanding. It is also the first step to realize automatic extraction from remote sensing images and is of great significance. As a large number of high resolution remote sensing images are obtained,traditional image segmentation methods are not meeting the rising demands of high resolution remote sensing image analysis. In recent years,object- based image analysis( OBIA) method is proposed by domestic and foreign researchers. The key of OBIA is image segmentation which directly influences the accuracy of high resolution remote sensing information extraction and target recognition. In this paper,a review of general image segmentation methods are firstly given,then remote sensing image segmentation methods which are widely used at present are summarized and analyzed. Characteristics and research status of methods such as Mean Shift algorithm,FNEA,MRF etc. are focused on. In the end,the development tendency of image segmentation in high resolution remote sensing application analysis is discussed and prospected.
引文
[1]Pohl C,Van Genderen J.Review article multisensor image fusion in remote sensing:concepts,methods and applications[J].International Journal of Remote Sensing,1998,19(5):823-854.
[2]元秀,晓阳.高分辨率卫星影像处理指南[M].北京:科学出版社,2008.
[3]章毓晋.图像工程[M].(第2版).北京:清华大学出版社有限公司,2005.
[4]BeaulieuJ M,Goldberg M.Hierarchy in picture segmentation:A stepwise optimization approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(2):150-163.
[5]Zhang Y,Gerbrands J J.Transition region determination based thresholding[J].Pattern Recognition Letters,1991,12(1):13-23.
[6]谈国军,戎皓.基于二维最大熵阈值图像分割技术的改进方法[J].软件导刊,2008(1):3-4.
[7]陈涛,卜佳俊.一种新颖的基于边缘检测的图像分割方法[J].计算机工程,2003,29(7):152-154.
[8]赵雪松,陈淑珍.综合全局二值化与边缘检测的图像分割方法[J].计算机辅助设计与图形学学报,2001,13(2):118-121.
[9]Chang Y L,Li X.Adaptive image region-growing[J].IEEE Transactions on Image Processing,1994,3(6):868-872.
[10]Strasters K C,Gerbrands J J.Three-dimensional image segmentation using a split,merge and group approach[J].Pattern Recognition Letters,1991,12(5):307-325.
[11]Banerjee S,Mukherjee D P,Dutta Majumdar D.Fuzzy C-means approach to tissue classification in multimodal medical imaging[J].Information Sciences,1999,115(1):261-279.
[12]刘志敏,杨杰.数学形态学的图象分割算法[J].计算机工程与科学,1998,20(4):21-27.
[13]Rout S,Srivastava P,Majumdar J.Multi-modal image segmentation using a modified Hopfield neural network[J].Pattern Recognition,1998,31(6):743-750.
[14]Malladi R,Sethian J A,Vemuri B C.Shape modeling with front propagation:A level set approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(2):158-175.
[15]Schiewe J.Segmentation of high-resolution remotely sensed data-concepts,applications and problems[J].International Archives of Photogrammetry Remote Sensing And Spatial Information Sciences,2002,34(4):380-385.
[16]Vincent L,Soille P.Watersheds in digital spaces:an efficient algorithm based on immersion simulations[J].IEEE transactions on pattern analysis and machine intelligence,1991,13(6):583-598.
[17]Huang X,Zhang L.An adaptive mean-shift analysis approach for object extraction and classification from urban hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(12):4 173-4 185.
[18]Happ P,Ferreira R,Bentes C,Costa G,Feitosa R.Multiresolution segmentation:a parallel approach for high resolution image segmentation in multicore architectures[C]//Proceedings of the 3rd International Conference on Geographic Object-Based Image Analysis,2010.
[19]梅天灿.高分辨率遥感影像中道路信息提取方法的研究[D].武汉:武汉大学测绘遥感信息工程国家重点实验室,2005.
[20]Akcay H G,Aksoy S.Automatic detection of geospatial objects using multiple hierarchical segmentations[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(7):2 097-2 111.
[21]Bruzzone L,Carlin L.A multilevel context-based system for classification of very high spatial resolution images[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(9):2 587-2 600.
[22]Castilla G.Size-contrained region merging:A new tool to derive basic landcover unit from remote sensing imagery[C]//Proceedings of ESAEUSC 2004,2004.
[23]王雷光.基于非模糊均值漂移的高空间分辨率遥感影像区域分割算法研究[D].武汉:武汉大学测绘遥感信息工程国家重点实验室,2009.
[24]Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[25]Blaschke T.Object based image analysis for remote sensing[J].ISPRS journal of photogrammetry and remote sensing,2010,65(1):2-16.
[26]Song M,Civco D.Road extraction using SVM and image segmentation[J].Photogrammetric engineering and remote sensing,2004,70(12):1 365-1 371.
[27]Yu Q,Gong P,Clinton N,Biging G,Kelly M,Schirokauer D.Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery[J].Photogrammetric engineering and remote sensing,2006,72(7):799.
[28]赵银娣,张良培,李平湘.广义马尔科夫随机场及其在多光谱纹理影像分类中的应用[J].遥感学报,2006,10(1):123-129.
[29]刘国英.基于小波域马尔科夫场的遥感影像分割研究[D].武汉:武汉大学测绘遥感信息工程国家重点实验室,2009.
[30]Zhao Y,Zhang L,Li P,Huang B.Classification of high spatial resolution imagery using improved Gaussian Markov random-field-based texture features[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(5):1458-1468.
[31]颜刚,陈武凡,冯衍秋.广义模糊Gibbs随机场与MR图像分割算法研究[J].中国图象图形学报,2005,10(9):1 082-1 088.
[32]Liu G,Wang L,Xie W,Qin Q,Li Y.New texture segmentation approach based on multiresoluton MRFs with variable weighting parameters in wavelet domain[C]//Proceedings of International Symposium on Multispectral Image Processing and Pattern Recognition.2007:67861O-67861O-8.
[33]Panjwani D K,Healey G.Markov random field models for unsupervised segmentation of textured color images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(10):939-954.
[34]Rellier G,Descombes X,Falzon F,Zerubia J.Texture feature analysis using a Gauss-Markov model in hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(7):1 543-1 551.
[35]Kato Z,Pong T C.A Markov random field image segmentation model for color textured images[J].Image and Vision Computing,2006,24(10):1 103-1 114.
[36]Bouman C A,Shapiro M.A multiscale random field model for Bayesian image segmentation[J].IEEE Transactions on Image Processing,1994,3(2):162-177.
[37]Crouse M S,Nowak R D,Baraniuk R G.Wavelet-based statistical signal processing using hidden Markov models[J].IEEE Transactions on Signal Processing,1998,46(4):886-902.
[38]Xia G S,He C,Sun H.An unsupervised segmentation method using Markov random field on region adjacency graph for SAR images[C]//Proceedings of IEEE International Conference on Radar.IEEE,2006:1-4.
[2]元秀,晓阳.高分辨率卫星影像处理指南[M].北京:科学出版社,2008.
[3]章毓晋.图像工程[M].(第2版).北京:清华大学出版社有限公司,2005.
[4]BeaulieuJ M,Goldberg M.Hierarchy in picture segmentation:A stepwise optimization approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(2):150-163.
[5]Zhang Y,Gerbrands J J.Transition region determination based thresholding[J].Pattern Recognition Letters,1991,12(1):13-23.
[6]谈国军,戎皓.基于二维最大熵阈值图像分割技术的改进方法[J].软件导刊,2008(1):3-4.
[7]陈涛,卜佳俊.一种新颖的基于边缘检测的图像分割方法[J].计算机工程,2003,29(7):152-154.
[8]赵雪松,陈淑珍.综合全局二值化与边缘检测的图像分割方法[J].计算机辅助设计与图形学学报,2001,13(2):118-121.
[9]Chang Y L,Li X.Adaptive image region-growing[J].IEEE Transactions on Image Processing,1994,3(6):868-872.
[10]Strasters K C,Gerbrands J J.Three-dimensional image segmentation using a split,merge and group approach[J].Pattern Recognition Letters,1991,12(5):307-325.
[11]Banerjee S,Mukherjee D P,Dutta Majumdar D.Fuzzy C-means approach to tissue classification in multimodal medical imaging[J].Information Sciences,1999,115(1):261-279.
[12]刘志敏,杨杰.数学形态学的图象分割算法[J].计算机工程与科学,1998,20(4):21-27.
[13]Rout S,Srivastava P,Majumdar J.Multi-modal image segmentation using a modified Hopfield neural network[J].Pattern Recognition,1998,31(6):743-750.
[14]Malladi R,Sethian J A,Vemuri B C.Shape modeling with front propagation:A level set approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(2):158-175.
[15]Schiewe J.Segmentation of high-resolution remotely sensed data-concepts,applications and problems[J].International Archives of Photogrammetry Remote Sensing And Spatial Information Sciences,2002,34(4):380-385.
[16]Vincent L,Soille P.Watersheds in digital spaces:an efficient algorithm based on immersion simulations[J].IEEE transactions on pattern analysis and machine intelligence,1991,13(6):583-598.
[17]Huang X,Zhang L.An adaptive mean-shift analysis approach for object extraction and classification from urban hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(12):4 173-4 185.
[18]Happ P,Ferreira R,Bentes C,Costa G,Feitosa R.Multiresolution segmentation:a parallel approach for high resolution image segmentation in multicore architectures[C]//Proceedings of the 3rd International Conference on Geographic Object-Based Image Analysis,2010.
[19]梅天灿.高分辨率遥感影像中道路信息提取方法的研究[D].武汉:武汉大学测绘遥感信息工程国家重点实验室,2005.
[20]Akcay H G,Aksoy S.Automatic detection of geospatial objects using multiple hierarchical segmentations[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(7):2 097-2 111.
[21]Bruzzone L,Carlin L.A multilevel context-based system for classification of very high spatial resolution images[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(9):2 587-2 600.
[22]Castilla G.Size-contrained region merging:A new tool to derive basic landcover unit from remote sensing imagery[C]//Proceedings of ESAEUSC 2004,2004.
[23]王雷光.基于非模糊均值漂移的高空间分辨率遥感影像区域分割算法研究[D].武汉:武汉大学测绘遥感信息工程国家重点实验室,2009.
[24]Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[25]Blaschke T.Object based image analysis for remote sensing[J].ISPRS journal of photogrammetry and remote sensing,2010,65(1):2-16.
[26]Song M,Civco D.Road extraction using SVM and image segmentation[J].Photogrammetric engineering and remote sensing,2004,70(12):1 365-1 371.
[27]Yu Q,Gong P,Clinton N,Biging G,Kelly M,Schirokauer D.Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery[J].Photogrammetric engineering and remote sensing,2006,72(7):799.
[28]赵银娣,张良培,李平湘.广义马尔科夫随机场及其在多光谱纹理影像分类中的应用[J].遥感学报,2006,10(1):123-129.
[29]刘国英.基于小波域马尔科夫场的遥感影像分割研究[D].武汉:武汉大学测绘遥感信息工程国家重点实验室,2009.
[30]Zhao Y,Zhang L,Li P,Huang B.Classification of high spatial resolution imagery using improved Gaussian Markov random-field-based texture features[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(5):1458-1468.
[31]颜刚,陈武凡,冯衍秋.广义模糊Gibbs随机场与MR图像分割算法研究[J].中国图象图形学报,2005,10(9):1 082-1 088.
[32]Liu G,Wang L,Xie W,Qin Q,Li Y.New texture segmentation approach based on multiresoluton MRFs with variable weighting parameters in wavelet domain[C]//Proceedings of International Symposium on Multispectral Image Processing and Pattern Recognition.2007:67861O-67861O-8.
[33]Panjwani D K,Healey G.Markov random field models for unsupervised segmentation of textured color images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(10):939-954.
[34]Rellier G,Descombes X,Falzon F,Zerubia J.Texture feature analysis using a Gauss-Markov model in hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(7):1 543-1 551.
[35]Kato Z,Pong T C.A Markov random field image segmentation model for color textured images[J].Image and Vision Computing,2006,24(10):1 103-1 114.
[36]Bouman C A,Shapiro M.A multiscale random field model for Bayesian image segmentation[J].IEEE Transactions on Image Processing,1994,3(2):162-177.
[37]Crouse M S,Nowak R D,Baraniuk R G.Wavelet-based statistical signal processing using hidden Markov models[J].IEEE Transactions on Signal Processing,1998,46(4):886-902.
[38]Xia G S,He C,Sun H.An unsupervised segmentation method using Markov random field on region adjacency graph for SAR images[C]//Proceedings of IEEE International Conference on Radar.IEEE,2006:1-4.