资源简介

摘要： 在给出端元的物理、代数和几何学解释基础上,对现有端元提取算法从算法设计机理出发,分为基于几何学、基于统计学和信号检测理论以及空间和光谱相结合三大类,并进一步对基于几何学的端元提取算法从技术处理手段差异细分为基于距离、体积、投影变换和最优化4种情况。结合端元提取算法分类,针对算法缺陷及改进思路,介绍了常见端元提取算法PPI、N-FINDR、UOSP、VCA、ICA、NMF和AMEE研究进展。最后,结合解混理论进展和工程应用实际,从技术综合和性能优化的角度指出了端元提取算法的研究展望。 关键词： 高光谱遥感;  端元提取;  线性光谱混合模型;  性能优化     Abstract: An explanation of endmember based on physics,algebra and geometry is described.And a classification,with three categories,of endmember extraction algorithms based on algorithm design theory is provided,namely,endmember extraction algorithms designed based on geometry,endmember extraction algorithms designed based on statistics and signal detection theory,and endmember extraction algorithms designed based on combination of spectral and spatial information.Furthmore,the category based on geometry can be subdivided into four conditions according to the different techniques,that is,distance,volume,projection and transformation,optimization.Owing to the classification of endmember extraction algorithms,the defects and improved techniques,research progress of some commonly endmember extraction algorithms including PPI,N\|Findr,UOSP,VCA,ICA,NMF,and AMEE are described.At last,from the point of view on engineering application of hyperspectral remote sensing and the development of unmixing theory,two research prospects on endmember extraction algorithm are pointed out.One prospect is combination of all different techniques used in endmember extraction,and the other is the performance optimization of existing algorithms. 

相关资源

1. 水质遥感监测的关键要素叶绿素a的反演算法研究进展
2. 基于无人机遥感技术的森林参数获取研究进展
3. 基于无线传感器网络的森林生态系统观测试验平台构建
4. 基于无人机激光雷达的森林冠层高度分析
5. 多源时序国产卫星影像的森林火灾动态监测
6. 基于无人机遥感技术的台风灾害倒伏绿化树木检测

下载说明

·如果您发现该资源不能下载，请通知管理员.gissky@gmail.com

·为确保下载的资源能正常使用，请使用[WinRAR v3.8]或以上版本解压本站资源,缺省解压密码www.gissky.net ，如果是压缩文件为分卷多文件，请依次下载每一个文件，并按照顺序命名为1.rar,2.rar,3.rar...，然后鼠标右击1.rar解压.

·为了保证您快速的下载速度，我们推荐您使用[网际快车]等专业工具下载.

·站内提供的资源纯属学习交流之用,如侵犯您的版权请与我们联系.