基于H-和改进C-均值的全极化SAR图像非监督分类

吴永辉; 计科峰; 郁文贤

doi:10.3724/SP.J.1146.2005.00635

基于H-和改进C-均值的全极化SAR图像非监督分类

doi: 10.3724/SP.J.1146.2005.00635

计量
- 文章访问数: 3728
- HTML全文浏览量: 104
- PDF下载量: 1026
- 被引次数: 0
出版历程
- 收稿日期: 2005-06-06
- 修回日期: 2005-11-28
- 刊出日期: 2007-01-19

Unsupervised Classification of Fully Polarimetric SAR Image Using H- Decomposition and Modified C-Mean Algorithm

摘要

摘要: 该文提出一种基于H-和改进C-均值的全极化SAR图像非监督分类方法。该方法先按H-对全极化SAR图像进行基于散射机理的分类，再将分类结果作为改进C-均值算法的初始类别划分，从而实现地物分类。迭代次数确定是C-均值动态聚类算法的关键，文中利用图像熵给出了一种新的迭代终止准则。与H-方法相比，该文方法能在保留分类结果物理散射机理的同时，实现有效的地物分类。NASA/JPL实验室AIRSAR系统获取的L波段旧金山全极化SAR数据的实验结果验证了该文方法的有效性。
- 极化合成孔径雷达;极化分解;分类
Abstract: A new method for unsupervised classification of terrain types using fully POLarimetric Synthetic Aperture Radar (POLSAR) data is proposed in this paper. The method is a combination of the unsupervised classification based on Cloudes H- decomposition and the modified C-mean algorithm. The fully polarimetric SAR image is initially classified using Cloudes method. The classification map is used as input of the modified C-mean algorithm, and then iteration is performed. It is important to determine the number of iteration in the modified C-mean algorithm, and a new termination criterion is presented using image entropy to do so. Compared with H- decomposition, not only scattering mechanisms of all classes can be preserved, but also terrain classification is effectively performed using this method. The effectiveness of this method is demonstrated using an L-band fully polarimetric SAR image of San Francisco, acquired by the NASA/JPL AIRSAR sensor.

HTML全文

参考文献(1)

[1] Ertin E and Potter L C. Polarimetric classification of scattering centers using M-ary Bayesian decision rules[J].IEEE Trans. on Aerospace and Electronic Systems.2000, 36(3):738-749 [2] Kouskoulas Y, Ulaby F T, and Pierce L E. The bayesian hierarchical classifier (BHC) and its application to short vegetation using multifrequency polarimetric SAR[J].IEEE Trans. on Geoscience and Remote Sensing.2004, 42(2):469-477 [3] Hellmann M, Jager G, Kratzschmar E, and Habermeyer M. Classification of full polarimetric SAR-data using artificial neural networks and fuzzy algorithms. Proc. IEEE International Geoscience and Remote Sensing Symposium, Hamburg, Germany, June 1999: 1995-1997. [4] Chen C T, Chen K S, and Lee J S. The use of fully polarimetric information for the fuzzy neural classification of SAR images[J].IEEE Trans. on Geoscience and Remote Sensing.2003, 41(9):2089-2100 [5] Fukuda S and Hirosawa H. A wavelet-based texture feature set applied to classification of multifrequency polarimetric SAR images[J].IEEE Trans. on Geoscience and Remote Sensing.1999, 37(5):2282-2286 [6] De Grandi G F, Lee J S, Simard M, Wakabayashi H, Schuler D, and Ainsworth T L. Speckle filtering, segmentation and classification of polarimetric SAR data: a unified approach based on the wavelet transform. Proc. IEEE International Geoscience and Remote Sensing Symposium, Honolulu, Hawaii, USA, July 2000: 1107-1109. [7] Kersten P R, Lee J S, Ainsworth T L, and Grunes M R. Classification of polarimetric synthetic aperture radar images using fuzzy clustering. IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, Greenbelt Maryland, USA, October, 2003: 150-156. [8] Aiazzi B, Alparone L, Baronti S, and Garzelli A. Land cover classification of built-up areas through enhanced fuzzy nearest-mean reclustering of textural features from X- and C-band polarimetric SAR data. Proc. SPIE, Barcelona, Spain, 2004, vol. 5236: 105-115. [9] van Zyl J J. Unsupervised classification of scattering behavior using radar polarimetry dada[J].IEEE Trans. on Geoscience and Remote Sensing.1989, 27(1):36-45 [10] Freeman A and Durden S. A three-component scattering model to describe polarimetric SAR data. Proc. SPIE, San Diego, USA, 1992, vol. 1748: 213-224. [11] Freeman A and Durden S. A three-component scattering model for polarimetric SAR data[J].IEEE Trans. on Geoscience and Remote Sensing.1998, 36(3):963-973 [12] Cloude S R and Pottier E. An entropy based classification scheme for land applications of polarimetric SAR[J].IEEE Trans. on Geoscience and Remote Sensing.1997, 35(1):68-78 [13] Cloude S R. An entropy based classification scheme for polarimetric SAR data. Proc. IEEE International Geoscience and Remote Sensing Symposium, Florence, Italy, July 1995: 2000-2002. [14] 边肇祺, 张学工等. 模式识别. 北京: 清华大学出版社, 2000, 1: 235-237.

施引文献

资源附件(0)

访问统计