Mean Shift遥感图像分割方法与应用研究
|
摘要
随着遥感技术的发展,对地观测系统已获取了海量各种类型遥感数据。现有研究表明,数据转化为信息存在许多不足,而遥感图像分割又是实现数据转化为信息过程中起着重要作用的一项关键技术,也是遥感图像处理领域的重点及难点课题。虽然已发展了大量的图像分割方法,并取得了一些研究成果,但应用到遥感图像分割中仍存在算法的适用性差、分割效率低、分割精度不高等不足。针对这些不足,本文拟采用Mean Shift算法进行遥感图像分割,充分利用图像的多维特征,自适应降噪的同时有效保留目标物体的边缘信息,以提高图像分割的精度和可靠性。本文研究工作主要包括：
(1)提出一种结合纹理特征的自适应带宽遥感图像分割方法,以解决Mean Shift算法分割精度不高的问题。传统Mean Shift算法只使用了图像的“位置-颜色”域特征,导致图像分割精度不高。该方法则充分利用遥感图像的“位置-颜色-纹理”域组成多维特征空间,发展自适应带宽策略。先对“位置-颜色”域特征数据进行聚类,再对聚类结果计算每一聚类区域的空间带宽、灰度带宽和纹理带宽,最后在“位置-颜色-纹理”域进行自适应聚类,得到分割结果。实验结果表明,该方法具有自适应性和稳健性,可以较好地提高遥感图像分割精度。
(2)引入一种区域合并方法,用于图像分割的后续处理中,以解决Mean Shift分割算法易产生的过分割问题。该方法先根据待处理遥感图像的空间分辨率确定固定空间带宽,再利用plug-in规则计算遥感图像每个波段的颜色带宽。采用基于区域面积加权的区域相似度准则和基于区域熵的合并停止准则来进行分割后的区域合并,从而解决过分割问题。
(3)提出了一种改进的快速遥感图像分割方法,以解决Mean Shift算法迭代时间长不适于处理海量的遥感图像的问题。针对影响Mean Shift算法的时间复杂度的各个变量分别提出加速策略；先利用固定带宽的高斯Mean Shift算法进行聚类得到超像素,再计算每个超像素的自适应带宽；最后采用基于区域的超像素融合来完成遥感图像分割,以达到快速地分割遥感图像。
(4)采用成熟的分割评价方法,用以评估遥感图像分割效果。对比分析了马丁误差估量法和对象级一致性误差估量法。实验比较得出：对象级一致性误差估量法是基于对象水平,能够很好地量化分割图像与参考图像之间的差异；相对于马丁误差估量法而言,对象级一致性误差估量法能够正确地反映分割图像中存在的过分割和欠分割状况,其评价结果与主观评价更加相符。
(5)发展一种基于Mean Shift遥感图像分割的道路提取方法。该方法首先应用Mean Shift算法实现道路图像的初步分割,再合并灰度相似的区域,并依据直方图选取最佳的阈值,进行二值化分割；然后引入形状因子去除混杂在图像中与道路形状特征不相似的区域,对于仍然与道路相连的非道路区域,则构造多方向形态学滤波对其进行剔除,从而分割出独立的道路区域,同时提取出道路线；最后连接断裂的道路线,实现道路网的提取。多组实验结果表明,该方法能很好地从复杂环境中提取道路网,特别是对直线型道路尤其有效。
最后,总结了本文的研究成果。下一步需要深入的研究工作有：(1)考虑分割的多尺度性,实现基于Mean Shift算法的多尺度遥感图像分割；(2)考虑利用Gabor滤波器来提取纹理特征,或将更多的特征如形状等特征用于Mean Shift遥感图像分割中。
With the development of remote sensing technology, abundant and various styles remote sensing data has been obtained from current earth observation system. Existing investigations show that there are many deficiencies in the process of data being translated to information, and remote sensing image segmentation is a key technology and difficult task of remote sensing image processing field. Large numbers of segmentation approaches have been developed, and some research progeny have been gained, but when these approaches are used to remote sensing image segmentation, there are also some defects such as limited adaptability, low segmentation efficiency, and low segmentation precision. Aiming at these defects and in order to improve segmentation precision and reliability, this paper improved classical Mean Shift algorithm to segment remote sensing images by fully useing multidimension feature of remote sensing images, it can be robustness to noise adaptively, as well as preserving edge information of object target effectively. The contents of this paper mainly include:
(1) In order to solve the low segmentation precision of Mean Shift algorithm in the process of segmenting remote sensing images, a segmentation approach utilizing texture features and adaptive bandwidths is proposed, Classical Mean Shift algorithm only uses the spatial-range features, and can easily lead to lower segmentation precision. While the proposed method uses the features of spatial-range-texture to form multi-dimension features spaces, and develop adaptive bandwidth strategy. Firstly data clustering is carried out in the space of position-range; then spatial bandwidth, range bandwidth and texture bandwidth of each region are calculated according to previous clustering results; lastly segmentation results are gotten by adaptive clustering in the space of position-range-texture. Experiment results show that the proposed method can improve segmentation precision of remote sensing images with high adaptability and robutness.
(2) In order to overcome the over-segmentation of classical Mean Shift algorithm, a region combination method is developed to postprocess the initial over-segmentation images. Firstly, spatial bandwidth is selected according to the resolution of remote sensing images under study; then spectrum bandwidths of each band are estimated by using plug-in rules; lastly, segmented regions were merged by using regions areas weighed similarity rule and region entropy based region merge stopping rules to solve over-segmentation problem of classical Mean Shift algorithm.
(3) An improved fast segmentation method is proposed in this paper, in order to solve long iterative time of classical Mean Shift algorithm, which is not apapt to mass remote sensing imageries. Aiming at fast segment remote sensing imagry, some accelerating strategies were proposed to solve each issue which affects time complication of classical Mean Shift algorithm. Firstly, super-pixels are gotten by using fixed bandwidths Gauss Mean Shift cluster algorithm. Then dandwidth of each super-pixel is calculated adaptively. Finally, remote sensing images segmentation is performed by using region-based super-pixels fusing process, and then high precision segmented results can be obtained.
(4) Mature segmentation evaluation method is adopted to evaluate remote sensing image segmentation. Martin error measure method and object-level consistency error meature method are contrastively analyzed firstly. The comparison experiments show that the object-level consistency error meature method works at the object level and can effectively measure the discrepancy between a segmented image and the reference image. Compared with Martin error measure method, object-level consistency error meature method can correctly reflect over-segmentation and under-segmentation of segmented images, and its evaluation result can be consistent with the subjective evaluation much better.
(5) A roads extraction method based on Mean Shift segmented remote sensing image is proposed. Firstly, road images are initially segmented by using Mean Shift algorithm, and regions with similar gray values are merged, and binarization segmentation is completed by selecting the optimal thresholds based on histogram of segmented images. Then shape indices are used to remove those regions mixed in image which have different shapes comparing to road; in order to ensure the independence of each road target candidate, a multidirectional morphological filtering algorithm is designed to separate road from the neighboring non-road objects, and then road lines are extracted. Finally, road network is extracted by connecting the broken road lines. Several experimental results show that the proposed method can be used to extract roads network from remote sensing images even under complex conditions, especially for the straight roads.
At last, after concluding all research work in this paper, further work need to be in-depth studied:(1) Consider multi-scale factors of remote sensing, and realize multi-scale remote sensing image segmentation based on Mean Shift algorithm.(2) Consider extracting textures features by using Gabor filter, or use more features such as shape features to segment remote sensing images based on Mean Shift algorithm.
(1)提出一种结合纹理特征的自适应带宽遥感图像分割方法,以解决Mean Shift算法分割精度不高的问题。传统Mean Shift算法只使用了图像的“位置-颜色”域特征,导致图像分割精度不高。该方法则充分利用遥感图像的“位置-颜色-纹理”域组成多维特征空间,发展自适应带宽策略。先对“位置-颜色”域特征数据进行聚类,再对聚类结果计算每一聚类区域的空间带宽、灰度带宽和纹理带宽,最后在“位置-颜色-纹理”域进行自适应聚类,得到分割结果。实验结果表明,该方法具有自适应性和稳健性,可以较好地提高遥感图像分割精度。
(2)引入一种区域合并方法,用于图像分割的后续处理中,以解决Mean Shift分割算法易产生的过分割问题。该方法先根据待处理遥感图像的空间分辨率确定固定空间带宽,再利用plug-in规则计算遥感图像每个波段的颜色带宽。采用基于区域面积加权的区域相似度准则和基于区域熵的合并停止准则来进行分割后的区域合并,从而解决过分割问题。
(3)提出了一种改进的快速遥感图像分割方法,以解决Mean Shift算法迭代时间长不适于处理海量的遥感图像的问题。针对影响Mean Shift算法的时间复杂度的各个变量分别提出加速策略；先利用固定带宽的高斯Mean Shift算法进行聚类得到超像素,再计算每个超像素的自适应带宽；最后采用基于区域的超像素融合来完成遥感图像分割,以达到快速地分割遥感图像。
(4)采用成熟的分割评价方法,用以评估遥感图像分割效果。对比分析了马丁误差估量法和对象级一致性误差估量法。实验比较得出：对象级一致性误差估量法是基于对象水平,能够很好地量化分割图像与参考图像之间的差异；相对于马丁误差估量法而言,对象级一致性误差估量法能够正确地反映分割图像中存在的过分割和欠分割状况,其评价结果与主观评价更加相符。
(5)发展一种基于Mean Shift遥感图像分割的道路提取方法。该方法首先应用Mean Shift算法实现道路图像的初步分割,再合并灰度相似的区域,并依据直方图选取最佳的阈值,进行二值化分割；然后引入形状因子去除混杂在图像中与道路形状特征不相似的区域,对于仍然与道路相连的非道路区域,则构造多方向形态学滤波对其进行剔除,从而分割出独立的道路区域,同时提取出道路线；最后连接断裂的道路线,实现道路网的提取。多组实验结果表明,该方法能很好地从复杂环境中提取道路网,特别是对直线型道路尤其有效。
最后,总结了本文的研究成果。下一步需要深入的研究工作有：(1)考虑分割的多尺度性,实现基于Mean Shift算法的多尺度遥感图像分割；(2)考虑利用Gabor滤波器来提取纹理特征,或将更多的特征如形状等特征用于Mean Shift遥感图像分割中。
With the development of remote sensing technology, abundant and various styles remote sensing data has been obtained from current earth observation system. Existing investigations show that there are many deficiencies in the process of data being translated to information, and remote sensing image segmentation is a key technology and difficult task of remote sensing image processing field. Large numbers of segmentation approaches have been developed, and some research progeny have been gained, but when these approaches are used to remote sensing image segmentation, there are also some defects such as limited adaptability, low segmentation efficiency, and low segmentation precision. Aiming at these defects and in order to improve segmentation precision and reliability, this paper improved classical Mean Shift algorithm to segment remote sensing images by fully useing multidimension feature of remote sensing images, it can be robustness to noise adaptively, as well as preserving edge information of object target effectively. The contents of this paper mainly include:
(1) In order to solve the low segmentation precision of Mean Shift algorithm in the process of segmenting remote sensing images, a segmentation approach utilizing texture features and adaptive bandwidths is proposed, Classical Mean Shift algorithm only uses the spatial-range features, and can easily lead to lower segmentation precision. While the proposed method uses the features of spatial-range-texture to form multi-dimension features spaces, and develop adaptive bandwidth strategy. Firstly data clustering is carried out in the space of position-range; then spatial bandwidth, range bandwidth and texture bandwidth of each region are calculated according to previous clustering results; lastly segmentation results are gotten by adaptive clustering in the space of position-range-texture. Experiment results show that the proposed method can improve segmentation precision of remote sensing images with high adaptability and robutness.
(2) In order to overcome the over-segmentation of classical Mean Shift algorithm, a region combination method is developed to postprocess the initial over-segmentation images. Firstly, spatial bandwidth is selected according to the resolution of remote sensing images under study; then spectrum bandwidths of each band are estimated by using plug-in rules; lastly, segmented regions were merged by using regions areas weighed similarity rule and region entropy based region merge stopping rules to solve over-segmentation problem of classical Mean Shift algorithm.
(3) An improved fast segmentation method is proposed in this paper, in order to solve long iterative time of classical Mean Shift algorithm, which is not apapt to mass remote sensing imageries. Aiming at fast segment remote sensing imagry, some accelerating strategies were proposed to solve each issue which affects time complication of classical Mean Shift algorithm. Firstly, super-pixels are gotten by using fixed bandwidths Gauss Mean Shift cluster algorithm. Then dandwidth of each super-pixel is calculated adaptively. Finally, remote sensing images segmentation is performed by using region-based super-pixels fusing process, and then high precision segmented results can be obtained.
(4) Mature segmentation evaluation method is adopted to evaluate remote sensing image segmentation. Martin error measure method and object-level consistency error meature method are contrastively analyzed firstly. The comparison experiments show that the object-level consistency error meature method works at the object level and can effectively measure the discrepancy between a segmented image and the reference image. Compared with Martin error measure method, object-level consistency error meature method can correctly reflect over-segmentation and under-segmentation of segmented images, and its evaluation result can be consistent with the subjective evaluation much better.
(5) A roads extraction method based on Mean Shift segmented remote sensing image is proposed. Firstly, road images are initially segmented by using Mean Shift algorithm, and regions with similar gray values are merged, and binarization segmentation is completed by selecting the optimal thresholds based on histogram of segmented images. Then shape indices are used to remove those regions mixed in image which have different shapes comparing to road; in order to ensure the independence of each road target candidate, a multidirectional morphological filtering algorithm is designed to separate road from the neighboring non-road objects, and then road lines are extracted. Finally, road network is extracted by connecting the broken road lines. Several experimental results show that the proposed method can be used to extract roads network from remote sensing images even under complex conditions, especially for the straight roads.
At last, after concluding all research work in this paper, further work need to be in-depth studied:(1) Consider multi-scale factors of remote sensing, and realize multi-scale remote sensing image segmentation based on Mean Shift algorithm.(2) Consider extracting textures features by using Gabor filter, or use more features such as shape features to segment remote sensing images based on Mean Shift algorithm.
引文
[1]Amo M, Martinez F, Torre M. Road Extraction from Aerial Images Using a Region Competition Algorithm [J]. IEEE Transactions on Image Processing,2006, 15(5):1192-1201.
[2]Arya S, Mount D, Netanyahu N, Silverman R, Wu A:An optimal algorithm for approximate nearest neighbor searching fixed dimensions. Journal of the ACM (JACM) 1998,45 (6):891-923.
[3]Boykov Y. and Jolly M. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images[C]. In International Conference on Computer vision, Volume I, July,2001:105-112.
[4]Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [C]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1124-1137.
[5]Carreira-Perpifin M A. Acceleration strategies for Gaussian mean shift image segmentation. In Proe of IEEE Conf. on Computer Vision and Pattern Recognition, Washington, DC:IEEE Computer Society,2006,1:1160-1167.
[6]Carreira-Perpinan M A, Williams C. On the Number of Modes of a Gaussian Mixture, In Proc. Of the 4th Int. Conf. on Scale-Space theories in Computer Vision, Heidelberg:Springer Berlin,2003:625-640.
[7]Carreira-Perpinan M A. Gaussian mean shift is an EM algorithm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(5): 767-776.
[8]Chen Q, Zhou C, Luo J, Ming D. Fast segmentation of high-resolution satellite images using watershed transform combined with an efficient region merging approach [C]. Lecture notes in computer science, Combinatorial Image Analysis, 2005, Volume 3322:621-630.
[9]Cheng Y Z. Mean shift, mode seeking, and clustering [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
[10]Collins R T. Mean Shift blob tracking through scales space, Proc. Of the Conf on Computer Vision and Pattern Recognition, Washington, DC:IEEE Computer Society,2003,2:234-240.
[11]Comaniciu D, Meer P. Mean shift analysis and applications. In Proc. of the IEEE Int. Conf. on Computer Vision. New York:IEEE Press,1999,2:1197-1203.
[12]Comanieiu D, Ramesh V, Meer P. Real-Time tracking of non-rigid objects using mean shift [C]. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR),2000:142-149.
[13]Comaniciu D, Ramesh V, Meer P. The variable bandwidth mean shift and data-driven scale selection [C]. In Proc. of the IEEE Int'l Conf. on Computer Vision, New York:IEEE Press,2001,1:438-445.
[14]Comanieiu D, Meer P. Mean shift:A robust approach toward feature space analysis. IEEE Trans. On pattern Analysis and Machine Intelligence,2002,24(5): 603-619.
[15]Comaniciu D. An Algorithm for Data-Driven Bandwidth Selection [C]. IEEE Trans. On Pattern Analysis and Machine Intelligence,2003,25(2):1-8.
[16]Cui J, Mei D L, Yu M Y, Zhou Y. Research of remote sensing image segmentation based on mean shift and region merging [C]. Applied Mechanics and Materials Vols,2011,90-93:2836-2839.
[17]Dai Qinling, Liu Guoying, Wang Cancai, Wang Leiguang. A remote sensing image segmentation method based on spectral and structure information fusion [J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Beijing 2008, Vol. XXXVII. Part B7:1215-1223.
[18]Dal Poz A P, Do Vale G M. Dynamic Programming Approach for Semi-Automated Road Extraction From Medium-And High-Resolution Images[C]. ISPRS Archives, Vol. ⅩⅩⅩⅣ, Part 3/W8, Munich,2003:17-19
[19]Dementhon D. Spatio-temporal segmentation of video by hierarchical mean shift analysis [C]. Proceedings of the Statistical Methods in Video Processing Workshop,2002:115-120.
[20]Elgammal A, Duraiswami R, Davis L. Effieient nonparametric adaptive color modeling using fast Gauss transforms [C]. In Proc. of Int'l Conf. Computer Vision and Pattern Recognition, New York:IEEE Press,2001,2:563-570.
[21]Elgammal A, Duraiswami R, Davis L. Efficient kernel density estimation using the fast gauss transform with applications to color modeling and tracking [C]. IEEE Transactions on Pattern Analysis and Machine Intelligence 2003,25 (11), 1499-1504.
[22]Fashing M, Tomasi C. Mean Shift is a Bound Optimization[C]. IEEE Trans. On Patten Analysis and Machine Intelligence,2005,27(3):471-474.
[23]Fukunaga K, Hostetler L D, The estimation of the gradient of a density function, with application in pattern recognition [J].IEEE Transactions on Information Theory,1975, IT-21(1):32-40.
[24]Fukunaga F, Hostetler L. Optimization of k-nearest-neighbor density estimates [J]. IEEE T. Information Theory,1973,19 (3):320-326.
[25]Georgescu B, Shimshoni I, Meer P. Mean shift based clustering in high dimensions:A texture classification example[C]. Proceedings of the IEEE International Conference on Computer Vision,2003,1:456-463.
[26]Gondra I, Xu T. Adaptive mean shift-based image segmentation using multiple instances learning [C]. In:Proceedings of the 3rd International Conference on Digital Information Management, London, UK:IEEE,2008:716-721.
[27]Gonzalez RC, Woods RE. Digital Image Processing Second Edition [M]. Prentice Hall, New York,2002:32-37.
[28]Gruen A, Li H H. Semiautomatic Linear Feature Extraction by Dynamic Programming and LSB-Snakes [J]. Photogrammet. Eng. Remote Sensing,1997, 63:985-995.
[29]Gruen A. Adaptive Least Squares Correlation—A Powerful Image Matching Technique [J]. South African Journal of Photogrammetry, Remote Sensing and Cartography,1985,14(3):175-187.
[30]Gruen A L. Semi-Automatic Linear Feature Extraction by Dynamic Programming and LSB-Snakes [J]. Photogrammetric Engineering and Remote Sensing,1997, 63(8):985-995.
[31]Guo Dahai, Weeks A, Klee H. Segmentations of road Area in High Resolution Images [C]. Geoscience and Remote Sensing Symposium, IGARSS 04. Proceedings.2004,6:3810-3813.
[32]Guo H, Guo P, Lu H. A Fast Mean Shift Procedure with New Iteration Strategy and Re-sampling [C]. IEEE International Conference on Systems, Man and Cybernetics,2006:2385-2389.
[33]Haralick R M, Shanmugam K, Dinstein I. Texture features for image classification [C]. IEEE Transactions on Systems, Man, and Cybernetics,1973, 3:610-621.
[34]Hong Yiping, Yi Jianqiang, Zhao Dongbin. Improved mean shift segmentation approach for natural images [J]. Applied Mathematics and Computation,2007, 185:940-952.
[35]Huang Jiaxiang, Li Shaozi, Zhou Changle, Extension of Mean Shift Vector with Theoretical Analysis and Experiment [C]. International Conference on Intelligent System and Knowledge Engineering,2008:1007-1012.
[36]Huang Xin, Zang Liangpei. An adaptive mean-shift analysis approach for object extraction and classification from urban hyperspectral imagery [J]. IEEE Transactions on Geosciences and Remote Sensing,2008,46(12):4175-4185.
[37]Innocentie E, Silvani X, Muzya A, et al. A software framework for fine grain parallelization of cellular models with Open MP:Application to fire spread [J]. Environmental Modeling & Software,2009(24):819-831.
[38]Jens N, Kaftan. Mean Shift Segmentation Evaluation of Optimization Techniques [C].International Conference on Computer Vision Theory and Application.2008: 365-374.
[39]Jimenez-Alaniz J R, Pohl-Alfaro M, Medina-Banuelos V, Yanez-Suarez O. Segmenting brain MRI using adaptive mean shift [C]. In:Proceedings of the 28th IEEE Conference on Engineering in Medicine and Biology Society, New York, 2006:3114-3117.
[40]Kartikeyan B, Sarkar A, Majumder K. A segmentation approach to classification of remote sensing imagery [J]. International Journal of Remote Sensing,1998,19: 1695-1709.
[41]Kass M, Withkin A. and Terzopoulos D. Snakes:Active contour models [J]. International Journal of Computer Vision.1988,1(4):321-331.
[42]Kovesti P D. MATLAB and Octave Functions for Computer Vision and Image Processing, School of Computer Science & Software Engineering [EB/OL]. http://www.csse.uwa.ede.au/-pk/research/matlabfns/,2000.
[43]Laprade RH. Split-and-merge segmentation of aerial photographs [J]. Computer Vision, Graphics and Image Processing,1988,48:77-86.
[44]Li Kun, Yang Ran, Qin Qianqing. Object-oriented Port Detection based on mean shift segmentation[C]. International Conference on Electrical and Control Engineering, Beijing,2010:1399-1403.
[45]Li Lei, Shu Ning. Object-Oriented Classification of High-Resolution Remote Sensing Image Using Structural Feature [C].3rd International Congress on Image and Signal Processing,2010:2212-2215.
[46]Lin Hui. Method of Image Segmentation on High-resolution Image and Classification for Land Covers [C]. Fourth International Conference on Natural Computation,2008:563-567.
[47]Lin Xiangguo, Zhang Jixian, Zheng Jun, Shen Jing. Semiautomatic road tracking by template matching and distance transform [J]. Urban Remote Sensing Event, 2009:1-7.
[48]Lu Bibo, Ku Yongxia, Wang Hui. Automatic Road Extraction Method Based on Level Set and ShapeAnalysis[C].Intelligent Computation Technology and Automation, Second International Conference,2009,3:511-514.
[49]Ma J, Xu L, Joulan M I. Asymptotic convergence rate of the EM algorithm for Gaussian mixture [C]. Neurocomputing,2000,12:2881-2907.
[50]Ma J, Xu L. Asymptotic convergence Properties of the EM algorithm, with respect to the overlap in mixture [C]. Neurocomputing,2005,68:105-129.
[51]Martin D. An Empirical Approach to Grouping and Segmentation. Ph.D.dissertation, U.C.Berkeley,2002:22-45.
[52]Martin D, Fowlkes C, Tal D, Malik J, A database of human segmented natural images and its application to evaluating algorithms and measuring ecological statistics [C]. Proceedings of the IEEE International Conference on Computer Vision 2001, V2:416-423.
[53]Mayer A, Greenspan H. An adaptive mean-shift framework for MRI brain segmentation [C]. IEEE Transactions on Medical Imaging,2009,28(8): 1238-1250.
[54]Mukherjee A, Parui S K, Chaudhuri D, Chaudhuri B B, Krishnan R. An Efficient Algorithm for Detection of Road-Like Structures in Satellite Images [C]. Pattern Recognition, Proceedings of the 13 th International Conference,1996,3:875-879.
[55]Oba S, Kato K, Ishii S. Multi-scale clustering for gene expression profiling data [C]. In Proc. Of the 5th IEEE Symposium on Bioinformatics and Bioengineering, New York:IEEE Press,2005:210-217.
[56]Ong S H, Hew C C. Segmentation of color image bases on iterative thresholding and merging [C]. Int Conf Processing APPL,1992:712-725.
[57]Pal NR, Pal SK. A review on image segmentation techniques [J]. Pattern Recognition,1993,26(9):1277-1294.
[58]Park A, Kim J, Min S, Yun S, Jung K. Graph cuts-based automatic color image segmentation using mean shift analysis.In:Proceedings of the Conference on Digital Image Computing:Techniques and Applications. Canberra, Australia: IEEE,2008.564-571.
[59]Paris S and Durand F. A topological approach to hierarchical segmentation using mean shift[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2007:2136-2143.
[60]Peng Pan, Gao Wei, Liu Xiuguo, Liu Xiuguo. An Improved Strategy for Object-Oriented Multi-Scale Remote Sensing Image Segmentation[C]. The 1st International Conference on Information Science and Engineering,2009, 1149-1153.
[61]Pilar Jarabo-Amores. Spatial-range mean-shift filtering and segmentation applied to SAR images [J]. IEEE Transactions on Instrumentation and Measurment,2011, 60(12):584-596.
[62]Polak M, Zhang H, and Pi M. An evaluation metric for image segmentation of multiple objects [J]. Image Vis. Computing,2009, vol 27,1223-1227.
[63]Poriki F, Tuzel O. Multi-kernel Object Tracking[C]. In Proc. of IEEE Int'l. Conf. on Multimedia and Expo, New York:IEEE Press,2005:1234-1237.
[64]Porikli F, Tuzel O. Human Body Tracking by Adaptive Background Models and Mean Shift Analysis[C]. In IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance,2003:1-11.
[65]Redner R A, Walker H F. Mixture densities, maximum likelihood and the EM algorithm [J]. SIAM Review,1984,26(2):195-239.
[66]Ren X, Malik J. Learning a dassification model for segmentation [C]. IEEE Iit. Conf. Computer Vision, Nice, France,2003,1:10-17.
[67]Ryherd S, Woodcock C. Combining spectral and texture data in the segmentation of remotely sensed images [J]. Photogrammetric Engineering & Remote Sensing, 1996,62(2):181-194.
[68]Shen C, Brooks M J, Hengel A. Fast Global Kernel Density Mode Seeking with application to Localisation and Tracking. In Proc. Of the 10th IEEE Int. Conf. on Computer Vision, New York:IEEE Press,2005,2:1516-1523.
[69]Shen Z, LUO J, HUANG G, et al. Distributed computing model for processing remotely sensed images based on grid computing [J]. Information Sciences, 2007(177):504-518.
[70]Sin C F, Leung C K. Image segmentation by edge pixel classification with maximum entropy [J]. IEEE Transactions on Intelligent Multimedia, Video and Speech Processing,2001:283-286.
[71]Singh M K, Ahuja N. Mean-shift segmentation with wavelet-based bandwidth selection[C]. In Proc. of the 6th IEEE Workshop on Applications of Computer Vision, New York:IEEE Press,2002:43-47.
[72]Singh M, Arora H, Ahuja N. A Robust Probabilistic Estimation Framework for Parametric Image Models. In European Conf. on Computer Vision, Heidelberg: Springer Berlin,2004,3021:508-522.
[73]Song Nuan, CAO Zhongping. Statistical-Based Image and Video Segmentation Using Mean Shift and Motion Field [D]. Chalmers University of Technology Goteborg, Sweden,2006:13-14.
[74]Toll D L. Effect of landsat thematic mapper sensor parameters on land covers classification [J]. Remote Sensing of Environment,1985a,17:129-140.
[75]Valmir C Barbosa, Ricardo J Machado, Frederico dos S Liporaee. A. neural system for deforestation monitoring on landsat images of the Amazon Region. International Journal of Approximate Reasoning,1994,11 (4):321-359.
[76]Wakahara T, Ogura K. Extended Mean Shift in Handwriting Clustering [C]. In Proc. of the 14th International Conference on Pattern Recognition, New York: IEEE Press,1998,1:384-388.
[77]Wang J, Thiesson B, Xu YQ, Cohen M. Image and Video Segmentation by Anisotropic Kernel Mean Shift[C]. In Proc. of European Conf. on Computer Vision, Springer-Verlag,2004,2:238-249.
[78]Wang P, Lee D, Gray A, Rehg J. Fast mean shift with accurate and stable convergence [C]. In Workshop on Artificial Intelligence and Statistics (AISTATS),2007:604-611.
[79]Woodcock C E, Strahler A H. The factor of scale in remote sensing [J]. Remote Sensing of Environment,1987,21:311-332.
[80]Wua K, Wang M, Mean shift-based clustering [J]. Pattern Recognition,2007, 40(11):3035-3052.
[81]XIE Qiang-jun, CHEN Xu, MA Li, et al. Segmentation for CT Image Based on Improved Level-Set Approach[C]. The 2008 International Congress on Image and Signal Processing,2008,3(3):725-728.
[82]Xu L, Jordan M I. on convergence properties of EM algorithm for Gaussian mixtures [M]. Neural Compute,1996,8:129-151.
[83]Yang A Y, Wright J, Ma Y. Unsupervised segmentation of natural images via lossy data compression[C], Computer Vision Image Understand,2008, 110:212-225.
[84]Yang C, Duraiswami R, DeMenthonand D, Davis L. Mean-Shift Analysis Using Quasi-Newton Methods [C]. In IEEE International Conference on Image Processing.2003(3):447-450.
[85]Yang C, Duraiswami R, and Davis L. Similarity Measure for Non-parametric Kernel Density Based Object Tracking. Eighteenth Annual Conference Neural Information Processing Systems.2005:1561-1568.
[86]Zhang K, Kwok J T, Tang M. Accelerated Convergence Using Dynamic Mean Shift, Proc. Of the European Conf. on Computer Vision, Graz, Austria, 2006:257-268.
[87]Zhang Lianjun, Zhang Jing, Zhang Dapeng, Hou Xiao Hui, Yang Gang. Urban Road Extraction from High Resolution Remote Sensing Images Based on Semantic Model[C]. Geoinformatics, International Conference,2010,1-5.
[88]Zhang YJ. Evaluation and comparison of different segmentation algorithms [J]. Pattern Recognition Letters,1997,18:963-974.
[89]Zhang Y J. A survey on evaluation methods for image segmentation. Pattern Recognition,1996,29(8):1335-1346.
[90]Zheng L Y, Zhang J T, Wang Q Y. Mean-shift-based color segmentation of images containing green vegetation. Computers and Electronics in Agriculture, 2009,65(1):93-98.
[91]Zlotnick A, Carnine PD. Finding road seeds in aerial images [J]. Image Understanding,1993,57:307-330.
[92]薄树奎,邸凤萍,李华玮,李盛阳,朱重光.基于均值漂移法进行多光谱遥感聚类研究[J].遥感信息,2006,5：17-20.
[93]蔡华杰,田金文.基于1mean-shift聚类过程的遥感影像自动分类方法[J].华中科技大学学报(自然科学版),2008,36(11)：1-4.
[94]蔡华杰,田金文.一种高分辩遥感影像多尺度分割新算法.武汉理工大学学报,2009,31(11)：97-100,121
[95]陈波,张友静,陈亮.标记分水岭算法及区域合并的遥感图像分割[J].国土资源遥感,2007,2：35-39.
[96]陈秋晓,陈述彭,周成虎.基于局域网同质性梯度的遥感图像分割方法及其评价[J].遥感学报,2006,10(3)：357-365.
[97]陈杰.高分辨率遥感影像面向对象分类方法研究[D].中南大学博士学位论文,2010,45-65.
[98]陈忠.高分辨率遥感图像分类技术研究[D].中国科学院遥感应用研究所博士学位论文,2006：97-106.
[99]耿振伟,蒋咏梅,粟毅,郁文贤.一种巨幅遥感影像中机场ROI检测算法[J].电子与信息学报,2005,27(11)：1770-1774.
[100]宫鹏,黎夏,徐冰.高分辨率影像解译理论与应用方法中的一些研究问题[J].遥感学报,2006,10(1)：1-5.
[101]顾丹丹,汪西莉.结合区域生长和水平集的遥感影像道路提取[J].计算机应用,2010,30(2)：433-440.
[102]郭庆昌.均值移动算法及在图像处理核目标跟踪中的应用研究.哈尔滨工程大学博士学位论文.2008：10-16.
[103]黄锐,桑农,罗大鹏,刘乐元.融合感知一致程度的图像分割评价方法[J].华中科技大学学报(自然科学版),2010a,38(10)：53-57.
[104]黄锐.图像线结构提取与区域分割方法研究[D].华中科技大学博士学位论文,2010b,5：65-67.
[105]胡进刚,张晓东,沈欣,张婵.一种面向对象的高分辨率影像道路提取方法[J].遥感技术与应用,2006,21(3)：184-190.
[106]贾永红.数字图像处理[M].武汉大学出版社,2003,132-133,182-184.
[107]刘海宾,何希勤,刘向东.基于分水岭和区域合并的图像分割算法[J].计算机应研究.2007,24(9)：307-308.
[108]刘少创,林宗坚.航空影像分割的Snake方法[J].武汉测绘科技大学学报,1995,20(1)：7-11.
[109]刘少创,林宗坚.彩色航空影像分割的OCTOPUS方法[J].中国图象图形学报,1997,2(11)：790-794.
[110]刘永学.面向对象的桐庐县标准农田遥感信息提取模式研究[D].南京大学博士学位论文,2004：51-56.
[111]李书晓,常红星.基于总变分和形态学的航空图像道路监测算法[J].计算机学报,2007,30(2)：2173-2180.
[112]李光,王朝英.改进的mean shift算法及在彩色图像分割中的应用[J].软件导刊,2010,9(1)：53-54.
[113]李艳灵,沈轶.基于共轭梯度法的快速Mean Shift图像分割[J].光电工程,2008,36(8)：94-99.
[114]李应岐,何明一,方小锋.基于Contourlet变换和均值漂移的SAR图像分割[J].计算机工程,2007,33(22)：48-50.
[115]李晓峰,张树清,韩富伟,秦喜文,于欢.基于多重信息融合的高分辨率遥感影像道路信息提取[J].测绘学报.2008,37(2)：178-184.
[116]李乡儒,吴福朝,吴战义.均值漂移算法的收敛性[J].软件学报.2005,16(3)： 365-374.
[117]莫登奎,林辉,李际平,孙华,熊育久.基于均值漂移的高分辨率影像多尺度分割[J].广西师范大学学报：自然科学版,2006,24(4)：247-250.
[118]逯贵祯,王玲,肖怀宝.基于均值漂移的SAR图像分割方法研究[J].中国传媒大学学报自然科学版,2009,16(2)：45-48.
[119]吕健刚,韦春桃.基于Hough变换的高分辨率遥感影像城市直线道路提取[J].遥感应用,2009(3)：15-18.
[120]彭宁嵩,杨杰等Mean Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9)：1542-1550.
[121]彭铁根,黄宴委,吴锡华.自适应带宽中值偏移视频图像分割研究[J].系统仿真学报,2005,17(9)：2115-2117.
[122]沈占锋,骆剑承,吴炜,胡晓东,遥感影像均值漂移分割算法的并行化实现[J].哈尔滨工业大学学报,2010a,42(5)：811-815.
[123]沈占锋,骆剑承,胡晓东,孙卫刚.高分辨率遥感影像多尺度均值漂移分割算法研究[J].武汉大学学报·信息科学版,2010b,35(3)：313-316
[124]陶超,谭毅华,蔡华杰等.面向对象的高分辨率遥感影像城区建筑物分级提取方法[J].测绘学报,2010,39(1)：39-45.
[125]陶文兵,金海.基于均值漂移滤波及谱分类的海面舰船红外目标分割[J].红外与毫米波学报,2007,26(1)：61-64.
[126]唐伟,赵书河,王培法.面向对象的高空间分辨率遥感影像道路信息的提取[J].地球信息科学,2008,10(2)：257-262.
[127]王衡霖,刘正军,沈伟.一种面向对象的遥感影像多尺度分割方法[J].北京交通大学学报,2007,31(4)
[128]王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京：科学出版社.2008：80-108.
[129]王凤兰,洪炳铬,曙光.基于颜色分布连续性特征的区域合并方法[J].哈尔滨工业大学学报.2003,35(9)：1086-1088.
[130]王雷光,刘国英,梅天灿,秦前清.一种光谱与纹理特征加权的高分辨率遥感纹理分割算法[J].光学学报,2009,29(11)：3000-3016.
[131]王雷光,郑晨,林立宇,陈荣元,梅天灿.基于多尺度均值漂移的高分辨率遥感影像快速分割方法[J].光谱学与光谱分析,2011,31(1)：178-183.
[132]王永忠,梁彦,赵春晖.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(4)：393-399.
[133]吴炜,沈占锋,骆剑承,陈秋晓,胡晓东.均值漂移高分辨率遥感影像多尺 度分割的集群实现[J].计算机工程与应用,2009,45(34)：7-10.
[134]文志强,蔡自兴Mean Shift算法的收敛性分析[J].软件学报,2007,18(2)：205-212.
[135]夏春林,张静,褚廷有.基于高分辨率城区遥感影像的道路半自动提取方法研究[J].测绘科学,2008,33(5)：140-142.
[136]肖飞,星光.图像分割方法综述[J].可编程控制器与工厂自动化,2009(11)：77-79.
[137]杨海峰.基于改进分水岭及区域合并的图像分割方法[J].微计算机应用,2007,28(11)：1132-1138.
[138]叶发茂,苏林,李树楷,汤江龙.高分辨率遥感影像提取道路的方法综述与思考[J].国土资源遥感,2006,67(1)：12-19.
[139]叶齐祥,高文,王伟强等.一种融合颜色和空间信息的彩色图像分割算法[J].软件学报,2004,15(4)：522-530.
[140]赵万磊,张学杰.基于RB-K平均带宽设定的Adaptive Mean shift[J]中国图象图形学报,2006,11(4)：511-515.
[141]张雷雨,邵永社,杨毅,韩阳.基于改进的Mean Shift方法的高分辨率遥感影像道路提取[J].遥感信息,2010,4：3-7.
[142]张秀英.面向对象的南京城区植被遥感方法研究[D].南京大学博士学位论文,2006：31-34.
[143]章毓晋.一种评价图像分割技术的新方法[J].模式识别与人工智能,1994,7(4)：299-304.
[144]周绍光,黎瑾慧.高分辨率遥感影像中提取复杂道路的新方法[J].计算机工程与应用,2008,44(35)：190-193.
[145]朱长青,王耀革,马秋禾,史文中.基于形态分割的高分辨率遥感影像道路提取[J].测绘学报,2004,33(4)：347-351.
[146]邹常文,刘先志,戴军,严发宝.基于多尺度分形与均值漂移的红外海面舰船目标分割[J].激光与红外,2010,40(9)：1023-1027.
[2]Arya S, Mount D, Netanyahu N, Silverman R, Wu A:An optimal algorithm for approximate nearest neighbor searching fixed dimensions. Journal of the ACM (JACM) 1998,45 (6):891-923.
[3]Boykov Y. and Jolly M. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images[C]. In International Conference on Computer vision, Volume I, July,2001:105-112.
[4]Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [C]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1124-1137.
[5]Carreira-Perpifin M A. Acceleration strategies for Gaussian mean shift image segmentation. In Proe of IEEE Conf. on Computer Vision and Pattern Recognition, Washington, DC:IEEE Computer Society,2006,1:1160-1167.
[6]Carreira-Perpinan M A, Williams C. On the Number of Modes of a Gaussian Mixture, In Proc. Of the 4th Int. Conf. on Scale-Space theories in Computer Vision, Heidelberg:Springer Berlin,2003:625-640.
[7]Carreira-Perpinan M A. Gaussian mean shift is an EM algorithm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(5): 767-776.
[8]Chen Q, Zhou C, Luo J, Ming D. Fast segmentation of high-resolution satellite images using watershed transform combined with an efficient region merging approach [C]. Lecture notes in computer science, Combinatorial Image Analysis, 2005, Volume 3322:621-630.
[9]Cheng Y Z. Mean shift, mode seeking, and clustering [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
[10]Collins R T. Mean Shift blob tracking through scales space, Proc. Of the Conf on Computer Vision and Pattern Recognition, Washington, DC:IEEE Computer Society,2003,2:234-240.
[11]Comaniciu D, Meer P. Mean shift analysis and applications. In Proc. of the IEEE Int. Conf. on Computer Vision. New York:IEEE Press,1999,2:1197-1203.
[12]Comanieiu D, Ramesh V, Meer P. Real-Time tracking of non-rigid objects using mean shift [C]. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR),2000:142-149.
[13]Comaniciu D, Ramesh V, Meer P. The variable bandwidth mean shift and data-driven scale selection [C]. In Proc. of the IEEE Int'l Conf. on Computer Vision, New York:IEEE Press,2001,1:438-445.
[14]Comanieiu D, Meer P. Mean shift:A robust approach toward feature space analysis. IEEE Trans. On pattern Analysis and Machine Intelligence,2002,24(5): 603-619.
[15]Comaniciu D. An Algorithm for Data-Driven Bandwidth Selection [C]. IEEE Trans. On Pattern Analysis and Machine Intelligence,2003,25(2):1-8.
[16]Cui J, Mei D L, Yu M Y, Zhou Y. Research of remote sensing image segmentation based on mean shift and region merging [C]. Applied Mechanics and Materials Vols,2011,90-93:2836-2839.
[17]Dai Qinling, Liu Guoying, Wang Cancai, Wang Leiguang. A remote sensing image segmentation method based on spectral and structure information fusion [J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Beijing 2008, Vol. XXXVII. Part B7:1215-1223.
[18]Dal Poz A P, Do Vale G M. Dynamic Programming Approach for Semi-Automated Road Extraction From Medium-And High-Resolution Images[C]. ISPRS Archives, Vol. ⅩⅩⅩⅣ, Part 3/W8, Munich,2003:17-19
[19]Dementhon D. Spatio-temporal segmentation of video by hierarchical mean shift analysis [C]. Proceedings of the Statistical Methods in Video Processing Workshop,2002:115-120.
[20]Elgammal A, Duraiswami R, Davis L. Effieient nonparametric adaptive color modeling using fast Gauss transforms [C]. In Proc. of Int'l Conf. Computer Vision and Pattern Recognition, New York:IEEE Press,2001,2:563-570.
[21]Elgammal A, Duraiswami R, Davis L. Efficient kernel density estimation using the fast gauss transform with applications to color modeling and tracking [C]. IEEE Transactions on Pattern Analysis and Machine Intelligence 2003,25 (11), 1499-1504.
[22]Fashing M, Tomasi C. Mean Shift is a Bound Optimization[C]. IEEE Trans. On Patten Analysis and Machine Intelligence,2005,27(3):471-474.
[23]Fukunaga K, Hostetler L D, The estimation of the gradient of a density function, with application in pattern recognition [J].IEEE Transactions on Information Theory,1975, IT-21(1):32-40.
[24]Fukunaga F, Hostetler L. Optimization of k-nearest-neighbor density estimates [J]. IEEE T. Information Theory,1973,19 (3):320-326.
[25]Georgescu B, Shimshoni I, Meer P. Mean shift based clustering in high dimensions:A texture classification example[C]. Proceedings of the IEEE International Conference on Computer Vision,2003,1:456-463.
[26]Gondra I, Xu T. Adaptive mean shift-based image segmentation using multiple instances learning [C]. In:Proceedings of the 3rd International Conference on Digital Information Management, London, UK:IEEE,2008:716-721.
[27]Gonzalez RC, Woods RE. Digital Image Processing Second Edition [M]. Prentice Hall, New York,2002:32-37.
[28]Gruen A, Li H H. Semiautomatic Linear Feature Extraction by Dynamic Programming and LSB-Snakes [J]. Photogrammet. Eng. Remote Sensing,1997, 63:985-995.
[29]Gruen A. Adaptive Least Squares Correlation—A Powerful Image Matching Technique [J]. South African Journal of Photogrammetry, Remote Sensing and Cartography,1985,14(3):175-187.
[30]Gruen A L. Semi-Automatic Linear Feature Extraction by Dynamic Programming and LSB-Snakes [J]. Photogrammetric Engineering and Remote Sensing,1997, 63(8):985-995.
[31]Guo Dahai, Weeks A, Klee H. Segmentations of road Area in High Resolution Images [C]. Geoscience and Remote Sensing Symposium, IGARSS 04. Proceedings.2004,6:3810-3813.
[32]Guo H, Guo P, Lu H. A Fast Mean Shift Procedure with New Iteration Strategy and Re-sampling [C]. IEEE International Conference on Systems, Man and Cybernetics,2006:2385-2389.
[33]Haralick R M, Shanmugam K, Dinstein I. Texture features for image classification [C]. IEEE Transactions on Systems, Man, and Cybernetics,1973, 3:610-621.
[34]Hong Yiping, Yi Jianqiang, Zhao Dongbin. Improved mean shift segmentation approach for natural images [J]. Applied Mathematics and Computation,2007, 185:940-952.
[35]Huang Jiaxiang, Li Shaozi, Zhou Changle, Extension of Mean Shift Vector with Theoretical Analysis and Experiment [C]. International Conference on Intelligent System and Knowledge Engineering,2008:1007-1012.
[36]Huang Xin, Zang Liangpei. An adaptive mean-shift analysis approach for object extraction and classification from urban hyperspectral imagery [J]. IEEE Transactions on Geosciences and Remote Sensing,2008,46(12):4175-4185.
[37]Innocentie E, Silvani X, Muzya A, et al. A software framework for fine grain parallelization of cellular models with Open MP:Application to fire spread [J]. Environmental Modeling & Software,2009(24):819-831.
[38]Jens N, Kaftan. Mean Shift Segmentation Evaluation of Optimization Techniques [C].International Conference on Computer Vision Theory and Application.2008: 365-374.
[39]Jimenez-Alaniz J R, Pohl-Alfaro M, Medina-Banuelos V, Yanez-Suarez O. Segmenting brain MRI using adaptive mean shift [C]. In:Proceedings of the 28th IEEE Conference on Engineering in Medicine and Biology Society, New York, 2006:3114-3117.
[40]Kartikeyan B, Sarkar A, Majumder K. A segmentation approach to classification of remote sensing imagery [J]. International Journal of Remote Sensing,1998,19: 1695-1709.
[41]Kass M, Withkin A. and Terzopoulos D. Snakes:Active contour models [J]. International Journal of Computer Vision.1988,1(4):321-331.
[42]Kovesti P D. MATLAB and Octave Functions for Computer Vision and Image Processing, School of Computer Science & Software Engineering [EB/OL]. http://www.csse.uwa.ede.au/-pk/research/matlabfns/,2000.
[43]Laprade RH. Split-and-merge segmentation of aerial photographs [J]. Computer Vision, Graphics and Image Processing,1988,48:77-86.
[44]Li Kun, Yang Ran, Qin Qianqing. Object-oriented Port Detection based on mean shift segmentation[C]. International Conference on Electrical and Control Engineering, Beijing,2010:1399-1403.
[45]Li Lei, Shu Ning. Object-Oriented Classification of High-Resolution Remote Sensing Image Using Structural Feature [C].3rd International Congress on Image and Signal Processing,2010:2212-2215.
[46]Lin Hui. Method of Image Segmentation on High-resolution Image and Classification for Land Covers [C]. Fourth International Conference on Natural Computation,2008:563-567.
[47]Lin Xiangguo, Zhang Jixian, Zheng Jun, Shen Jing. Semiautomatic road tracking by template matching and distance transform [J]. Urban Remote Sensing Event, 2009:1-7.
[48]Lu Bibo, Ku Yongxia, Wang Hui. Automatic Road Extraction Method Based on Level Set and ShapeAnalysis[C].Intelligent Computation Technology and Automation, Second International Conference,2009,3:511-514.
[49]Ma J, Xu L, Joulan M I. Asymptotic convergence rate of the EM algorithm for Gaussian mixture [C]. Neurocomputing,2000,12:2881-2907.
[50]Ma J, Xu L. Asymptotic convergence Properties of the EM algorithm, with respect to the overlap in mixture [C]. Neurocomputing,2005,68:105-129.
[51]Martin D. An Empirical Approach to Grouping and Segmentation. Ph.D.dissertation, U.C.Berkeley,2002:22-45.
[52]Martin D, Fowlkes C, Tal D, Malik J, A database of human segmented natural images and its application to evaluating algorithms and measuring ecological statistics [C]. Proceedings of the IEEE International Conference on Computer Vision 2001, V2:416-423.
[53]Mayer A, Greenspan H. An adaptive mean-shift framework for MRI brain segmentation [C]. IEEE Transactions on Medical Imaging,2009,28(8): 1238-1250.
[54]Mukherjee A, Parui S K, Chaudhuri D, Chaudhuri B B, Krishnan R. An Efficient Algorithm for Detection of Road-Like Structures in Satellite Images [C]. Pattern Recognition, Proceedings of the 13 th International Conference,1996,3:875-879.
[55]Oba S, Kato K, Ishii S. Multi-scale clustering for gene expression profiling data [C]. In Proc. Of the 5th IEEE Symposium on Bioinformatics and Bioengineering, New York:IEEE Press,2005:210-217.
[56]Ong S H, Hew C C. Segmentation of color image bases on iterative thresholding and merging [C]. Int Conf Processing APPL,1992:712-725.
[57]Pal NR, Pal SK. A review on image segmentation techniques [J]. Pattern Recognition,1993,26(9):1277-1294.
[58]Park A, Kim J, Min S, Yun S, Jung K. Graph cuts-based automatic color image segmentation using mean shift analysis.In:Proceedings of the Conference on Digital Image Computing:Techniques and Applications. Canberra, Australia: IEEE,2008.564-571.
[59]Paris S and Durand F. A topological approach to hierarchical segmentation using mean shift[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2007:2136-2143.
[60]Peng Pan, Gao Wei, Liu Xiuguo, Liu Xiuguo. An Improved Strategy for Object-Oriented Multi-Scale Remote Sensing Image Segmentation[C]. The 1st International Conference on Information Science and Engineering,2009, 1149-1153.
[61]Pilar Jarabo-Amores. Spatial-range mean-shift filtering and segmentation applied to SAR images [J]. IEEE Transactions on Instrumentation and Measurment,2011, 60(12):584-596.
[62]Polak M, Zhang H, and Pi M. An evaluation metric for image segmentation of multiple objects [J]. Image Vis. Computing,2009, vol 27,1223-1227.
[63]Poriki F, Tuzel O. Multi-kernel Object Tracking[C]. In Proc. of IEEE Int'l. Conf. on Multimedia and Expo, New York:IEEE Press,2005:1234-1237.
[64]Porikli F, Tuzel O. Human Body Tracking by Adaptive Background Models and Mean Shift Analysis[C]. In IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance,2003:1-11.
[65]Redner R A, Walker H F. Mixture densities, maximum likelihood and the EM algorithm [J]. SIAM Review,1984,26(2):195-239.
[66]Ren X, Malik J. Learning a dassification model for segmentation [C]. IEEE Iit. Conf. Computer Vision, Nice, France,2003,1:10-17.
[67]Ryherd S, Woodcock C. Combining spectral and texture data in the segmentation of remotely sensed images [J]. Photogrammetric Engineering & Remote Sensing, 1996,62(2):181-194.
[68]Shen C, Brooks M J, Hengel A. Fast Global Kernel Density Mode Seeking with application to Localisation and Tracking. In Proc. Of the 10th IEEE Int. Conf. on Computer Vision, New York:IEEE Press,2005,2:1516-1523.
[69]Shen Z, LUO J, HUANG G, et al. Distributed computing model for processing remotely sensed images based on grid computing [J]. Information Sciences, 2007(177):504-518.
[70]Sin C F, Leung C K. Image segmentation by edge pixel classification with maximum entropy [J]. IEEE Transactions on Intelligent Multimedia, Video and Speech Processing,2001:283-286.
[71]Singh M K, Ahuja N. Mean-shift segmentation with wavelet-based bandwidth selection[C]. In Proc. of the 6th IEEE Workshop on Applications of Computer Vision, New York:IEEE Press,2002:43-47.
[72]Singh M, Arora H, Ahuja N. A Robust Probabilistic Estimation Framework for Parametric Image Models. In European Conf. on Computer Vision, Heidelberg: Springer Berlin,2004,3021:508-522.
[73]Song Nuan, CAO Zhongping. Statistical-Based Image and Video Segmentation Using Mean Shift and Motion Field [D]. Chalmers University of Technology Goteborg, Sweden,2006:13-14.
[74]Toll D L. Effect of landsat thematic mapper sensor parameters on land covers classification [J]. Remote Sensing of Environment,1985a,17:129-140.
[75]Valmir C Barbosa, Ricardo J Machado, Frederico dos S Liporaee. A. neural system for deforestation monitoring on landsat images of the Amazon Region. International Journal of Approximate Reasoning,1994,11 (4):321-359.
[76]Wakahara T, Ogura K. Extended Mean Shift in Handwriting Clustering [C]. In Proc. of the 14th International Conference on Pattern Recognition, New York: IEEE Press,1998,1:384-388.
[77]Wang J, Thiesson B, Xu YQ, Cohen M. Image and Video Segmentation by Anisotropic Kernel Mean Shift[C]. In Proc. of European Conf. on Computer Vision, Springer-Verlag,2004,2:238-249.
[78]Wang P, Lee D, Gray A, Rehg J. Fast mean shift with accurate and stable convergence [C]. In Workshop on Artificial Intelligence and Statistics (AISTATS),2007:604-611.
[79]Woodcock C E, Strahler A H. The factor of scale in remote sensing [J]. Remote Sensing of Environment,1987,21:311-332.
[80]Wua K, Wang M, Mean shift-based clustering [J]. Pattern Recognition,2007, 40(11):3035-3052.
[81]XIE Qiang-jun, CHEN Xu, MA Li, et al. Segmentation for CT Image Based on Improved Level-Set Approach[C]. The 2008 International Congress on Image and Signal Processing,2008,3(3):725-728.
[82]Xu L, Jordan M I. on convergence properties of EM algorithm for Gaussian mixtures [M]. Neural Compute,1996,8:129-151.
[83]Yang A Y, Wright J, Ma Y. Unsupervised segmentation of natural images via lossy data compression[C], Computer Vision Image Understand,2008, 110:212-225.
[84]Yang C, Duraiswami R, DeMenthonand D, Davis L. Mean-Shift Analysis Using Quasi-Newton Methods [C]. In IEEE International Conference on Image Processing.2003(3):447-450.
[85]Yang C, Duraiswami R, and Davis L. Similarity Measure for Non-parametric Kernel Density Based Object Tracking. Eighteenth Annual Conference Neural Information Processing Systems.2005:1561-1568.
[86]Zhang K, Kwok J T, Tang M. Accelerated Convergence Using Dynamic Mean Shift, Proc. Of the European Conf. on Computer Vision, Graz, Austria, 2006:257-268.
[87]Zhang Lianjun, Zhang Jing, Zhang Dapeng, Hou Xiao Hui, Yang Gang. Urban Road Extraction from High Resolution Remote Sensing Images Based on Semantic Model[C]. Geoinformatics, International Conference,2010,1-5.
[88]Zhang YJ. Evaluation and comparison of different segmentation algorithms [J]. Pattern Recognition Letters,1997,18:963-974.
[89]Zhang Y J. A survey on evaluation methods for image segmentation. Pattern Recognition,1996,29(8):1335-1346.
[90]Zheng L Y, Zhang J T, Wang Q Y. Mean-shift-based color segmentation of images containing green vegetation. Computers and Electronics in Agriculture, 2009,65(1):93-98.
[91]Zlotnick A, Carnine PD. Finding road seeds in aerial images [J]. Image Understanding,1993,57:307-330.
[92]薄树奎,邸凤萍,李华玮,李盛阳,朱重光.基于均值漂移法进行多光谱遥感聚类研究[J].遥感信息,2006,5：17-20.
[93]蔡华杰,田金文.基于1mean-shift聚类过程的遥感影像自动分类方法[J].华中科技大学学报(自然科学版),2008,36(11)：1-4.
[94]蔡华杰,田金文.一种高分辩遥感影像多尺度分割新算法.武汉理工大学学报,2009,31(11)：97-100,121
[95]陈波,张友静,陈亮.标记分水岭算法及区域合并的遥感图像分割[J].国土资源遥感,2007,2：35-39.
[96]陈秋晓,陈述彭,周成虎.基于局域网同质性梯度的遥感图像分割方法及其评价[J].遥感学报,2006,10(3)：357-365.
[97]陈杰.高分辨率遥感影像面向对象分类方法研究[D].中南大学博士学位论文,2010,45-65.
[98]陈忠.高分辨率遥感图像分类技术研究[D].中国科学院遥感应用研究所博士学位论文,2006：97-106.
[99]耿振伟,蒋咏梅,粟毅,郁文贤.一种巨幅遥感影像中机场ROI检测算法[J].电子与信息学报,2005,27(11)：1770-1774.
[100]宫鹏,黎夏,徐冰.高分辨率影像解译理论与应用方法中的一些研究问题[J].遥感学报,2006,10(1)：1-5.
[101]顾丹丹,汪西莉.结合区域生长和水平集的遥感影像道路提取[J].计算机应用,2010,30(2)：433-440.
[102]郭庆昌.均值移动算法及在图像处理核目标跟踪中的应用研究.哈尔滨工程大学博士学位论文.2008：10-16.
[103]黄锐,桑农,罗大鹏,刘乐元.融合感知一致程度的图像分割评价方法[J].华中科技大学学报(自然科学版),2010a,38(10)：53-57.
[104]黄锐.图像线结构提取与区域分割方法研究[D].华中科技大学博士学位论文,2010b,5：65-67.
[105]胡进刚,张晓东,沈欣,张婵.一种面向对象的高分辨率影像道路提取方法[J].遥感技术与应用,2006,21(3)：184-190.
[106]贾永红.数字图像处理[M].武汉大学出版社,2003,132-133,182-184.
[107]刘海宾,何希勤,刘向东.基于分水岭和区域合并的图像分割算法[J].计算机应研究.2007,24(9)：307-308.
[108]刘少创,林宗坚.航空影像分割的Snake方法[J].武汉测绘科技大学学报,1995,20(1)：7-11.
[109]刘少创,林宗坚.彩色航空影像分割的OCTOPUS方法[J].中国图象图形学报,1997,2(11)：790-794.
[110]刘永学.面向对象的桐庐县标准农田遥感信息提取模式研究[D].南京大学博士学位论文,2004：51-56.
[111]李书晓,常红星.基于总变分和形态学的航空图像道路监测算法[J].计算机学报,2007,30(2)：2173-2180.
[112]李光,王朝英.改进的mean shift算法及在彩色图像分割中的应用[J].软件导刊,2010,9(1)：53-54.
[113]李艳灵,沈轶.基于共轭梯度法的快速Mean Shift图像分割[J].光电工程,2008,36(8)：94-99.
[114]李应岐,何明一,方小锋.基于Contourlet变换和均值漂移的SAR图像分割[J].计算机工程,2007,33(22)：48-50.
[115]李晓峰,张树清,韩富伟,秦喜文,于欢.基于多重信息融合的高分辨率遥感影像道路信息提取[J].测绘学报.2008,37(2)：178-184.
[116]李乡儒,吴福朝,吴战义.均值漂移算法的收敛性[J].软件学报.2005,16(3)： 365-374.
[117]莫登奎,林辉,李际平,孙华,熊育久.基于均值漂移的高分辨率影像多尺度分割[J].广西师范大学学报：自然科学版,2006,24(4)：247-250.
[118]逯贵祯,王玲,肖怀宝.基于均值漂移的SAR图像分割方法研究[J].中国传媒大学学报自然科学版,2009,16(2)：45-48.
[119]吕健刚,韦春桃.基于Hough变换的高分辨率遥感影像城市直线道路提取[J].遥感应用,2009(3)：15-18.
[120]彭宁嵩,杨杰等Mean Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9)：1542-1550.
[121]彭铁根,黄宴委,吴锡华.自适应带宽中值偏移视频图像分割研究[J].系统仿真学报,2005,17(9)：2115-2117.
[122]沈占锋,骆剑承,吴炜,胡晓东,遥感影像均值漂移分割算法的并行化实现[J].哈尔滨工业大学学报,2010a,42(5)：811-815.
[123]沈占锋,骆剑承,胡晓东,孙卫刚.高分辨率遥感影像多尺度均值漂移分割算法研究[J].武汉大学学报·信息科学版,2010b,35(3)：313-316
[124]陶超,谭毅华,蔡华杰等.面向对象的高分辨率遥感影像城区建筑物分级提取方法[J].测绘学报,2010,39(1)：39-45.
[125]陶文兵,金海.基于均值漂移滤波及谱分类的海面舰船红外目标分割[J].红外与毫米波学报,2007,26(1)：61-64.
[126]唐伟,赵书河,王培法.面向对象的高空间分辨率遥感影像道路信息的提取[J].地球信息科学,2008,10(2)：257-262.
[127]王衡霖,刘正军,沈伟.一种面向对象的遥感影像多尺度分割方法[J].北京交通大学学报,2007,31(4)
[128]王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京：科学出版社.2008：80-108.
[129]王凤兰,洪炳铬,曙光.基于颜色分布连续性特征的区域合并方法[J].哈尔滨工业大学学报.2003,35(9)：1086-1088.
[130]王雷光,刘国英,梅天灿,秦前清.一种光谱与纹理特征加权的高分辨率遥感纹理分割算法[J].光学学报,2009,29(11)：3000-3016.
[131]王雷光,郑晨,林立宇,陈荣元,梅天灿.基于多尺度均值漂移的高分辨率遥感影像快速分割方法[J].光谱学与光谱分析,2011,31(1)：178-183.
[132]王永忠,梁彦,赵春晖.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(4)：393-399.
[133]吴炜,沈占锋,骆剑承,陈秋晓,胡晓东.均值漂移高分辨率遥感影像多尺 度分割的集群实现[J].计算机工程与应用,2009,45(34)：7-10.
[134]文志强,蔡自兴Mean Shift算法的收敛性分析[J].软件学报,2007,18(2)：205-212.
[135]夏春林,张静,褚廷有.基于高分辨率城区遥感影像的道路半自动提取方法研究[J].测绘科学,2008,33(5)：140-142.
[136]肖飞,星光.图像分割方法综述[J].可编程控制器与工厂自动化,2009(11)：77-79.
[137]杨海峰.基于改进分水岭及区域合并的图像分割方法[J].微计算机应用,2007,28(11)：1132-1138.
[138]叶发茂,苏林,李树楷,汤江龙.高分辨率遥感影像提取道路的方法综述与思考[J].国土资源遥感,2006,67(1)：12-19.
[139]叶齐祥,高文,王伟强等.一种融合颜色和空间信息的彩色图像分割算法[J].软件学报,2004,15(4)：522-530.
[140]赵万磊,张学杰.基于RB-K平均带宽设定的Adaptive Mean shift[J]中国图象图形学报,2006,11(4)：511-515.
[141]张雷雨,邵永社,杨毅,韩阳.基于改进的Mean Shift方法的高分辨率遥感影像道路提取[J].遥感信息,2010,4：3-7.
[142]张秀英.面向对象的南京城区植被遥感方法研究[D].南京大学博士学位论文,2006：31-34.
[143]章毓晋.一种评价图像分割技术的新方法[J].模式识别与人工智能,1994,7(4)：299-304.
[144]周绍光,黎瑾慧.高分辨率遥感影像中提取复杂道路的新方法[J].计算机工程与应用,2008,44(35)：190-193.
[145]朱长青,王耀革,马秋禾,史文中.基于形态分割的高分辨率遥感影像道路提取[J].测绘学报,2004,33(4)：347-351.
[146]邹常文,刘先志,戴军,严发宝.基于多尺度分形与均值漂移的红外海面舰船目标分割[J].激光与红外,2010,40(9)：1023-1027.