多尺度对象高空间分辨率遥感影像谱聚类分割
|
摘要
针对基于像素模型的单尺度或多尺度谱聚类影像分割方法在相似矩阵存储、特征分解效率及分割精度方面存在的不足。该文首先通过给定多组空间及光谱带宽参数,利用mean-shift初分割生成不同尺度的超像素对象层;然后联合像素与超像素对高空间分辨率影像中的不同类别地物进行的多尺度建模表达其空间拓扑关系,即在图割理论框架下建立"像素-超像素"联合的多尺度无向权图模型G(V,E,W),同时根据遥感影像纹理特征丰富的特点,在顶点相似性计算过程中融合纹理特征;最后使用基于normalized cut准则的谱聚类算法,对图模型划分得到最终分割结果。该方法较好地降低了基于像素的谱聚类分割方法的计算复杂度,同时提高分割结果准确率。标准测试数据集和"高分2号"遥感影像分割结果表明了该方法的有效性。
According to the shortcomings in storage of similarity matrix,inefficiency of eigenvector decomposition and the accuracy of segmentation using pixel based single-scale or multi-scale spectral clustering.First,different space and range domain bandwidth parameters were given to generate different scale super-pixel layer by mean-shift algorithm.Then,pixels and multi-layer superpixels were used to model the high spatial resolution remote sensing imagery to represent its topology structure,that is construct a"pixel-superpixel"based undirectional weighted graph model under the graph cut theory,and we also optimized the method to calculate the vertex whose connected with each other to finish similarity matrix.Finally,a spectral clustering algorithm based on normalized cut criterion was used to partition the graph model and get the final segmentation result.This method reduces the computational complexity while improve segmentation accuracy of pixel-based spectral clustering.The segmentation results of standard images database and GF2 remote sensing images show that the method is effective.
According to the shortcomings in storage of similarity matrix,inefficiency of eigenvector decomposition and the accuracy of segmentation using pixel based single-scale or multi-scale spectral clustering.First,different space and range domain bandwidth parameters were given to generate different scale super-pixel layer by mean-shift algorithm.Then,pixels and multi-layer superpixels were used to model the high spatial resolution remote sensing imagery to represent its topology structure,that is construct a"pixel-superpixel"based undirectional weighted graph model under the graph cut theory,and we also optimized the method to calculate the vertex whose connected with each other to finish similarity matrix.Finally,a spectral clustering algorithm based on normalized cut criterion was used to partition the graph model and get the final segmentation result.This method reduces the computational complexity while improve segmentation accuracy of pixel-based spectral clustering.The segmentation results of standard images database and GF2 remote sensing images show that the method is effective.
引文
[1] ZENG S,HUANG R,KANG Z,et al.Image segmentation using spectral clustering of Gaussian mixture models[J].Neurocomputing,2014,144:346-356.
[2] LUXBURG U V.A tutorial on spectral clustering[J].Statistics and Computing,2007,17(4):395-416.
[3] WU Z,LEAHY R.An optimal graph theoretic approach to data clustering:theory and its application to image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1101-1113.
[4] SHI J B,MALIK J.Normalized cuts and image segmentation[C]∥Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,1997:731-737.
[5]袁永华,李玉,赵雪梅.基于谱聚类的高分辨率全色遥感影像分割[J].仪器仪表学报,2016,37(7):1656-1664.(YUAN Yonghua,LI Yu,ZHAO Xuemei.Highresolution panchromatic remote sensing image segmentation based on spectral clustering[J].Chinese Journal of Scientific Instrument,2016,37(7):1656-1664.)
[6]张向荣,骞晓雪,焦李成.基于免疫谱聚类的图像分割[J].软件学报,2010,21(9):2196-2205.(ZHANG Xiangrong,QIAN Xiaoxue,JIAO Licheng.Immune spectral clustering algorithm for image segmentation[J].Journal of Software,2010,21(9):2196-2205.)
[7] TOUSSI S A,YAZDI H S,HAJINEZHAD E,et al.Eigenvector selection in spectral clustering using Tabu Search[C]∥International Econference on Computer and Knowledge Engineering.[S.l.]:IEEE,2013:75-80.
[8] COUR T,BENEZIT F,SHI J B.Spectral segmentation with multiscale graph decomposition[C]∥2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).Washington:IEEE Computer Society,2005:1124-1131.
[9]刘仲民,李战明,李博皓,等.基于稀疏矩阵的谱聚类图像分割算法[J].吉林大学学报(工学版),2017,47(4):1308-1313.(LIU Zhongmin,LI Zhanming,LI Bohao,et al.Spectral clustering image segmentation based on sparse matrix[J].Journal of Jilin University(Engineering and Technology Edition),2017,47(4):1308-1313.
[10]GUI Y,BAI X,LI Z,et al.Color image segmentation using mean shift and improved spectral clustering[C]∥The 12th International Conference on Control Automation Robotics&Vision(ICARCV).[S.l.]:IEEE,2012:1386-1391.
[11]CHENG H D,JIANG X H,SUN Y,et al.Color image segmentation:advances and prospects[J].Pattern Recognition,2001,34(12):2259-2281.
[12]GOLUB G H,VAN LOAN C F.Matrix computations[M].3rd ed.Baltimore:Johns Hopkins University Press,1983.
[13]YU S X,SHI J B.Multiclass spectral clustering[C]∥Proceedings of the Ninth IEEE International Conference on Computer Vision.Washington:IEEE Computer Society,2003:313-319.
[14]LI Z G,WU X M,CHANG S F.Segmentation using superpixels:a bipartite graph partitioning approach[C]∥2012IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,2012:789-796.
[15]KIM T H,LEE K M,LEE S U.Learning full pairwise affinities for spectral segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(7):1690-1703.
[16]KOHLI P,LADICKY L,TORR P H S.Robust higher order potentials for enforcing label consistency[C]∥2008IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2008:1-8.
[17]COMANICIU D,MEER P.Mean shift:a robust approach toward feature space analysis[J]IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[18]宋熙煜,周利莉,李中国,等.图像分割中的超像素方法研究综述[J].中国图象图形学报,2015,20(5):599-608.(SONG Xiyi,ZHOU Lili,LI Zhongguo,et al.Review on superpixel methods in image segmentation[J].Journal of Image and Graphics,2015,20(5):599-608.)
[19]HARALICK R M,SHANMUGAM K,DINSTEIN I.Textural features for image classification[J].IEEE Transactions on Systems,Man,and Cybernetics,1973,SMC-3(6):610-621.
[20]ZHA H Y,HE X F,DING C,et al.Bipartite graph partitioning and data clustering[C]∥Proceedings of the Tenth International Conference on Information and Knowledge Management.New York:ACM,2001:25-32.
[21]ZHONG Y,GAO R,ZHANG L.Multiscale and multifeature normalized cut segmentation for high spatial resolution remote sensing imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(10):6061-6075.
[22]MARTIN D,FOWLKES C,TAL D,et al.A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]∥Proceedings of the Eighth IEEE International Conference on Computer Vision.[S.l.]:[s.n.],2001:416-423.
[23]UNNIKRISHNAN R,PANTOFARU C,HEBERT M.Toward objective evaluation of image segmentation algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):929-944.
[2] LUXBURG U V.A tutorial on spectral clustering[J].Statistics and Computing,2007,17(4):395-416.
[3] WU Z,LEAHY R.An optimal graph theoretic approach to data clustering:theory and its application to image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1101-1113.
[4] SHI J B,MALIK J.Normalized cuts and image segmentation[C]∥Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,1997:731-737.
[5]袁永华,李玉,赵雪梅.基于谱聚类的高分辨率全色遥感影像分割[J].仪器仪表学报,2016,37(7):1656-1664.(YUAN Yonghua,LI Yu,ZHAO Xuemei.Highresolution panchromatic remote sensing image segmentation based on spectral clustering[J].Chinese Journal of Scientific Instrument,2016,37(7):1656-1664.)
[6]张向荣,骞晓雪,焦李成.基于免疫谱聚类的图像分割[J].软件学报,2010,21(9):2196-2205.(ZHANG Xiangrong,QIAN Xiaoxue,JIAO Licheng.Immune spectral clustering algorithm for image segmentation[J].Journal of Software,2010,21(9):2196-2205.)
[7] TOUSSI S A,YAZDI H S,HAJINEZHAD E,et al.Eigenvector selection in spectral clustering using Tabu Search[C]∥International Econference on Computer and Knowledge Engineering.[S.l.]:IEEE,2013:75-80.
[8] COUR T,BENEZIT F,SHI J B.Spectral segmentation with multiscale graph decomposition[C]∥2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05).Washington:IEEE Computer Society,2005:1124-1131.
[9]刘仲民,李战明,李博皓,等.基于稀疏矩阵的谱聚类图像分割算法[J].吉林大学学报(工学版),2017,47(4):1308-1313.(LIU Zhongmin,LI Zhanming,LI Bohao,et al.Spectral clustering image segmentation based on sparse matrix[J].Journal of Jilin University(Engineering and Technology Edition),2017,47(4):1308-1313.
[10]GUI Y,BAI X,LI Z,et al.Color image segmentation using mean shift and improved spectral clustering[C]∥The 12th International Conference on Control Automation Robotics&Vision(ICARCV).[S.l.]:IEEE,2012:1386-1391.
[11]CHENG H D,JIANG X H,SUN Y,et al.Color image segmentation:advances and prospects[J].Pattern Recognition,2001,34(12):2259-2281.
[12]GOLUB G H,VAN LOAN C F.Matrix computations[M].3rd ed.Baltimore:Johns Hopkins University Press,1983.
[13]YU S X,SHI J B.Multiclass spectral clustering[C]∥Proceedings of the Ninth IEEE International Conference on Computer Vision.Washington:IEEE Computer Society,2003:313-319.
[14]LI Z G,WU X M,CHANG S F.Segmentation using superpixels:a bipartite graph partitioning approach[C]∥2012IEEE Conference on Computer Vision and Pattern Recognition.Washington:IEEE Computer Society,2012:789-796.
[15]KIM T H,LEE K M,LEE S U.Learning full pairwise affinities for spectral segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(7):1690-1703.
[16]KOHLI P,LADICKY L,TORR P H S.Robust higher order potentials for enforcing label consistency[C]∥2008IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2008:1-8.
[17]COMANICIU D,MEER P.Mean shift:a robust approach toward feature space analysis[J]IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[18]宋熙煜,周利莉,李中国,等.图像分割中的超像素方法研究综述[J].中国图象图形学报,2015,20(5):599-608.(SONG Xiyi,ZHOU Lili,LI Zhongguo,et al.Review on superpixel methods in image segmentation[J].Journal of Image and Graphics,2015,20(5):599-608.)
[19]HARALICK R M,SHANMUGAM K,DINSTEIN I.Textural features for image classification[J].IEEE Transactions on Systems,Man,and Cybernetics,1973,SMC-3(6):610-621.
[20]ZHA H Y,HE X F,DING C,et al.Bipartite graph partitioning and data clustering[C]∥Proceedings of the Tenth International Conference on Information and Knowledge Management.New York:ACM,2001:25-32.
[21]ZHONG Y,GAO R,ZHANG L.Multiscale and multifeature normalized cut segmentation for high spatial resolution remote sensing imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(10):6061-6075.
[22]MARTIN D,FOWLKES C,TAL D,et al.A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]∥Proceedings of the Eighth IEEE International Conference on Computer Vision.[S.l.]:[s.n.],2001:416-423.
[23]UNNIKRISHNAN R,PANTOFARU C,HEBERT M.Toward objective evaluation of image segmentation algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):929-944.