| 基于独立分量分析的高光谱影像小目标提取研究 |
| |
| 引用本文： | 路威,余旭初,刘德刚.基于独立分量分析的高光谱影像小目标提取研究[J].武汉大学学报(信息科学版),2005,30(12):1071-1074. |
| |
| 作者姓名： | 路威 余旭初 刘德刚 |
| |
| 作者单位： | 信息工程大学测绘学院,郑州市陇海中路66号,450052 |
| |
| 基金项目： | 国家863计划资助项目(2002AA783050) |
| |
| 摘 要： | 借助快速独立分量分析(FICA)将高维数据中隐藏的目标信息集中投影到低维特征影像中,然后以峰度为特征度量指标选择特征影像,最后用以偏斜为指标的直方图分割方法提取小目标。实验证明,此算法精度较高,适用于对高光谱影像中的小目标进行提取。
|
| 关 键 词： | 快速独立分量分析 偏斜 峰度 目标提取 |
| 文章编号： | 1671-8860(2005)12-1071-04 |
| 收稿时间： | 2005-10-22 |
| 修稿时间： | 2005年10月22 |
Research on Small Targets Extraction Based on ICA in Hyperspectral |
| |
| LU Wei,YU Xuchu,LIU Degang.Research on Small Targets Extraction Based on ICA in Hyperspectral[J].Geomatics and Information Science of Wuhan University,2005,30(12):1071-1074. |
| |
| Authors: | LU Wei YU Xuchu LIU Degang |
| |
| Institution: | 1, Institute of Surveying and Mapping, Information Engineering University, 66 Middle Longhai Road,Zhengzhou 450052,China |
| |
| Abstract: | This paper present a small targets detection approach based on independent component analysis in hyperspectral data.Firstly,this algorithm uses fast independent component analysis(FICA) approach to collect the targets information hided in the high-dimensional data and projects them into low-dimensional space.Secondly,selects feature images with kurtosis.At last,extracts small targets with histogram image segmentation method which has been labeled by skewness. |
| |
| Keywords: | fast independent component analysis skewness kurtosis targets extraction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
