| 基于SL-ICA算法的SAR图像混合像元分解 |
| |
| 引用本文： | 曹恒智,余先川,张立保.基于SL-ICA算法的SAR图像混合像元分解[J].遥感学报,2009,13(2):217-223. |
| |
| 作者姓名： | 曹恒智 余先川 张立保 |
| |
| 作者单位： | 北京师范大学信息科学与技术学院,北京,100875 |
| |
| 基金项目： | 北京市自然科学基金，国家自然科学基金，教育部新世纪优秀人才支持计划 |
| |
| 摘 要： | 为解决合成孔径雷达(SAR)图像存在大量混合像元的问题,针对传统ICA不能有效解决混合像元分解这一缺陷,提出一种新的独立成分分析算法--有监督学习ICA算法(SL-ICA).其目标函数是在原ICA负熵目标函数基础上增加监督学习的约束条件项,进而在同一目标函数内实现负熵和约束条件的统一,在最大化负熵的同时也最小化了约束条件的误差,此外,采用一种新的双梯度下降法优化迭代,提高计算速度.并以人工模拟SAR图像和北京地区ENVISAT-ASAR作为数据源进行实验,实验结果明显优于主成分分析方法(PCA)的分解结果.
|
| 关 键 词： | 合成孔径雷达 混合像元分解 独立成分分析 遥感影像 主成分分析 |
Decomposition of SAR images' mixed pixels based on supervised learning ICA algorithm |
| |
| CAO Heng-zhi,YU Xian-chuan and ZHANG Li-bao.Decomposition of SAR images'' mixed pixels based on supervised learning ICA algorithm[J].Journal of Remote Sensing,2009,13(2):217-223. |
| |
| Authors: | CAO Heng-zhi YU Xian-chuan and ZHANG Li-bao |
| |
| Affiliation: | College of Information Science and Technology, Beijing Normal University,Beijing 100875, China;College of Information Science and Technology, Beijing Normal University,Beijing 100875, China;College of Information Science and Technology, Beijing Normal University,Beijing 100875, China |
| |
| Abstract: | Forresolving theproblem thatthere are lotsofmixed pixels in the SyntheticApertureRadar(SAR) images, againstthe
flaw that the traditional IndependentComponentAnalysis(ICA) can not solve the decomposition ofmixed pixels effectively, we
propose a new algorithm: Supervised Learning ICA algorithm(SL-ICA). Adding supervised learning restrictive conditions to the
negentropy objective function, we implementnegentropy and restrictive conditions in a unified objective function, whichminimizes
the errorwhilemaximizing the negentropy. At the same time, we optimize the objective function using a new dual-gradientdescent
algorithm iteratively, which accelerates the computing speed. By testing SL-ICA and PrincipalComponentAnalysis (PCA). on
artificial simulated SAR images and ENVISAT-ASAR (Advanced SyntheticApertureRadar) images ofBeijing, the results show
thatSL-ICA can getmore precise results than the PCA. |
| |
| Keywords: | Synthetic Aperture Radar (SAR) decomposition of mixed pixels Independent Component Analysis (ICA) remote sensing image Principal Component Analysis(PCA) |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《遥感学报》浏览原始摘要信息 |
|
点击此处可从《遥感学报》下载全文 |
|
