L1-Endmembers: A Robust Endmember Detection andSpectral Unmixing Algorithm

摘要

A hyperspectral endmember detection and spectral unmixing algorithm based on an 11 norm factoriza-tion of the input hyperspectral data is developed and compared to a method based on 12 norm factoriza-tion. Both algorithms, the L1-Endmembers algorithm based on the l_1norm and the SPICE algorithmbased on the 12 norm, simultaneously and autonomously estimate endmember spectra, abundance val-ues and the number of endmembers needed for a hyperspectral image. The 11 norm factorization ofthe hyperspectral data is approximated through the use of the Huber M-estimator. Results showingthe stability of the L1-Endmembers algorithm in terms of the number of endmembers estimated withnoise and outliers are presented. Results indicate that the proposed algorithm is more consistent inestimating the correct number of endmembers over SPICE. However, when both algorithms determinethe correct number of endmembers, SPICE results provide a better estimate of endmembers and a lowervariance of endmember estimates over many runs with random initialization.