Target Detection Algorithm in Hyperspectral Imagery Based on FastICA

摘要：

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 FastICA 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.

关键词： Independent Component Analysis Noise-Adjusted Principal Component Analysis Unsupervised Orthogonal Subspace Projection Hyperspectral Imagery Endmember extraction

作者: ZHENG Mao ZAN Decai ZHANG Wenxi

作者单位: School of Electronic Science and Engineering,National University of Defense Technology,Changsha,4100 Computer Network Department,Hebei Engineering and Technical College,Cangzhou,061001,P.R.China Dept.Electronic and Communication Engineering,Changsha University,Changsha,410003,P.R.China

会议类型: 国际会议

会议名称: The 2nd IEEE International Conference on Advanced Computer Control(第二届先进计算机控制国际会议 ICACC 2010)

会议地点: 沈阳

会议语种:英文

页码: 579-582

在线出版日期: 2010-03-27（万方平台首次上网日期，不代表论文的发表时间）