2017/11/08 by Jérémy E. Cohen, Jeremy E. Cohen, Nicolas Gillis
Chemistry · Earth and Planetary Sciences · Engineering · Mathematics · #Computer science #Geology #Remote Sensing and Land Use #Remote sensing #Remote-Sensing Image Classification #Spectroscopy and Chemometric Analyses #math.OC
paper · pdf · doi:10.1109/lgrs.2017.2779477
published as IEEE Geoscience and Remote Sensing Letters 15 (2), pp. 187-191, 2018
arxiv created 2017/11/08 · openalex publication_date 2017/12/27 · arxiv updated 2018/02/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Spectral unmixing aims at recovering the spectral signatures of materials, called endmembers, mixed in a hyperspectral image (HSI) or multispectral image, along with their abundances. A typical assumption is that the image contains one pure pixel per endmember, in which case spectral unmixing reduces to identifying these pixels. Many fully automated methods have been proposed in recent years, but little work has been done to allow users to select areas where pure pixels are present manually or using a segmentation algorithm. Additionally, in a nonblind approach, several spectral libraries may be available rather than a single one, with a fixed number (or an upper or lower bound) of endmembers to chose from each. In this letter, we propose a multiple-dictionary constrained low-rank matrix approximation model that addresses these two problems. We propose an algorithm to compute this model, dubbed multiple matching pursuit alternating least squares, and its performance is discussed on both synthetic and real HSIs.