Discussion of the BSS's Application for Hyperspectral Imagery Unmixing

• 作 者: LiLIANG;KeGUO;SongpuXU;LingCHEN;
• 机 构: Geomathematics Key Laboratory of Sichuan Province,Chengdu University of Technology,Chengdu,China,610
• 出 处: 2011年信息技术、服务科学与工程管理国际学术会议
• 发表日期: 2011年期

　　The problem of blind signal separation is that the mixed signals need to be separated without knowing the mixing matrix and the source signals.The paper analyses and compares the algorithm and application of ICA and NMF,which are the traditional and improved algorithm of FastICA and the NMF based on Euclidean distance.Finally it is pointed out that the faced problems of hyperspectral remote sensing unmixing by the methods of blind signal separation.