摘要
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.
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.
基金
Funded by the National 863 Program of China (No.2002AA783050)
