| Small Target Extraction Based on Independent Component Analysis for Hyperspectral Imagery |
| |
| 作者姓名： | LU Wei YU Xuchu |
| |
| 作者单位： | Institute of Communication Engineering,2 Biaoying Road,Nanjing 210007, China |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | IntroductionFeature extraction or transformation is a key stepfor target detection in hyperspectral imagery. Thepurpose is to transform the high-dimensional imageinto low-dimensional image series so that the differ-ences between the targets and the backgr…
|
| 关 键 词： | 偏斜 峰度 卫星摄影测量 数据处理 |
| 文章编号： | 1009-5020（2006）02-103-05 |
| 收稿时间： | 2006-02-20 |
Small target extraction based on independent component analysis for hyperspectral imagery |
| |
| LU Wei YU Xuchu.Small Target Extraction Based on Independent Component Analysis for Hyperspectral Imagery[J].Geo-Spatial Information Science,2006,9(2):103-107. |
| |
| Authors: | Lu Wei PhD Yu Xuchu |
| |
| Institution: | LU Wei YU Xuchu |
| |
| Abstract: | A small target detection approach based on independent component analysis for hyperspectral data is put forward. In this algorithm, firstly the fast independent component analysis(FICA) is used to collect target information hided in high-dimensional data and projects them into low-dimensional space.Secondly, the feature images are selected with kurtosis .At last, small targets are extracted with histogram image segmentation which has been labeled by skewness. |
| |
| Keywords: | fast independent component analysis skewness kurtosis target extraction |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
