基于谱聚类的极化SAR影像分割改进算法

魏思奇; 张 煜; 叶 松

doi:10.11988/ckyyb.20160820

PDF(1338 KB)

长江科学院院报 ›› 2016, Vol. 33 ›› Issue (11) : 28-31. DOI: 10.11988/ckyyb.20160820

遥感技术应用

基于谱聚类的极化SAR影像分割改进算法

魏思奇,张煜,叶松

作者信息 +

Polarimetric SAR Image Segmentation Algorithmby Spectral Clustering

WEI Si-qi, ZHANG Yu, YE Song

Author information +

文章历史 +

摘要

谱聚类的影像分割算法是一种基于点的聚类方法,其通过选用不同的特征构建相似性度量矩阵,来衡量像元间的相似性程度。在解算过程中需要计算每2个像元间的相似性度量,在处理大幅影像时,运算量大、耗时长。针对这一问题,提出了一种改进方法。首先通过均值漂移算法对极化SAR影像进行预处理,然后选取中心像元,构建相似性度量矩阵,采用归一化分割准则完成影像分割。实验结果表明,该算法分割结果优良,准确性高,有效地提高了原算法的分割效率,具有一定的实践意义。

Abstract

Image segmentation by spectral clustering is a clustering method based on points. It is characterized by the use of similarity measure matrixes. We usually need to calculate the similarity matrixes between every two cells, which consumes huge computation task and a lot of time when processing large images. To solve this problem, we propose an improved method. First, we use mean shift algorithm for polarimetric SAR image, and then select center pixel to construct similarity measure matrix. At last, we use the normalized segmentation rule for image segmentation. Computation experiment proves that the algorithm could improve the efficiency with high accuracy and satisfactory result, hence is of practical significance.

导出引用

魏思奇,张煜,叶松. 基于谱聚类的极化SAR影像分割改进算法[J]. 长江科学院院报. 2016, 33(11): 28-31 https://doi.org/10.11988/ckyyb.20160820

WEI Si-qi, ZHANG Yu, YE Song. Polarimetric SAR Image Segmentation Algorithmby Spectral Clustering[J]. Journal of Changjiang River Scientific Research Institute. 2016, 33(11): 28-31 https://doi.org/10.11988/ckyyb.20160820

中图分类号： TP317.4

参考文献

[1] BENZ U, POTTIER E. Object Based Analysis of Polarimetric SAR Data in Alpha-Entropy-Anisotropy Decomposition Using Fuzzy Classification by eCognition∥Proceedings of the IEEE 2011 International Geoscience and Remote Sensing Symposium. Australia, 2011:1426-1428. DOI: 10.1109/IGARSS.2001.976867.
[2]吴永辉,计科峰,李禹,等.基于Wishart分布和MRF的多视全极化SAR图像分割.电子学报,2012,35(12):2302-2306.
[3]邹同元,杨文,代登信,等.一种新的极化SAR图像非监督分类算法研究.武汉大学学报(信息科学版),2009,34(8):910-913.
[4]张杰.极化SAR影像的分割.青岛:山东科技大学,2012.
[5]张艳梅.融合极化和纹理特征的SAR影像面向对象分类.青岛:山东科技大学,2012.
[6]VAHID A, ANTHONY P, GABRIELE M, et al. A Textural Contextual Model for Unsupervised Segmentation of Multi-polarization Synthetic Aperture Radar Images. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(4):2442-2453.
[7]李乡儒,吴福朝,胡占义.均值漂移算法的收敛性[J].软件学报,2012,16(3):366-375.
[8]SHI J, MALIK J. Normalized Cuts and Image Segmentation. IEEE Transactions on PAMI, 2011, 22(8): 887-903.
[9]LIU B, HU H, WANG Huan-yu, et al. Superpixel-based Classification with an Adaptive Number of Classes for Polarimetric SAR Images. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(2): 907-924.
[10]WEBB A R.统计模式识别(第二版).王萍等译.北京:电子工业出版社,2004.