Image Processing and Machine Learning for Hyperspectral Unmixing: An Overview and the HySUPP Python Package

• Published in: IEEE transactions on geoscience and remote sensing Vol. 62; no. 5517631; pp. 1 - 31
• Main Authors: Rasti, Behnood, Zouaoui, Alexandre, Mairal, Julien, Chanussot, Jocelyn
• Format: Journal Article
• Language: English
• Published: New York IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Abundance estimation; Atmospheric modeling; Computer Science; Computer Vision and Pattern Recognition; deep learning (DL); endmember extraction; hyperspectral; Hyperspectral imaging; Image Processing; Learning algorithms; linear mixture; Machine Learning; machine learning (ML); Mathematical models; Matlab; Mixtures; optimization; Pixels; Python; Reflectivity; Spatial discrimination; Spatial resolution; unmixing; Deep learning; Hyperspectral; Endmember extraction; Machine learning; Linear mixture; Abundance estimation; Optimization; Unmixing
• ISSN: 0196-2892; 1558-0644; 1558-0644
• DOI: 10.1109/TGRS.2024.3393570

Spectral pixels are often a mixture of the pure spectra of the materials, called endmembers, due to the low spatial resolution of hyperspectral sensors, double scattering, and intimate mixtures of materials in the scenes. Unmixing estimates the fractional abundances of the endmembers within the pixel. Depending on the prior knowledge of endmembers, linear unmixing can be divided into three main groups: supervised, semi-supervised, and unsupervised (blind) linear unmixing. Advances in image processing and machine learning (ML) substantially affected unmixing. This article provides an overview of advanced and conventional unmixing approaches. In addition, we draw a critical comparison between advanced and conventional techniques from the three categories. We compare the performance of the unmixing techniques on three simulated and one real dataset. The experimental results reveal the advantages of different unmixing categories for different unmixing scenarios. Moreover, we provide an open-source Python-based package available at https://github.com/BehnoodRasti/HySUPP to reproduce the results.