Target detection algorithm in hyperspectral imagery based on FastICA

The target detection algorithm based on Independent Component Analysis (ICA) was proposed. The orthogonal subspace projection operator was used to extract the target endmembers and the initialization mixing matrix of the FastõICA was made up of such endmember vectors. This method could solve the ordering randomicity of independent vectors. In this paper, the Noise-Adjusted Principal Component Analysis (NAPCA) was used to reduce the dimensionality of the original data to reduce the calculation. The ICA transformation of the reserved principal components was developed to detect the targets. The experimental results based on AVIRIS hyperspectral imagery have shown that it is more effective than the CEM method.