Translator Disclaimer
Presentation + Paper
12 April 2021 Supervised unconstrained and constrained least squares unmixing in hyperspectral imagery
Author Affiliations +
Spectral mixture analysis of hyperspectral imagery allows for detection, classification and quantification of targets present in the imaged scene. It can be difficult to characterize the performance of spectral unmixing techniques at detection, classification and quantification of field data at the subpixel level due to limited ground truth, especially for mixed pixels. Fortunately, the SpecTIR Hyperspectral Airborne Experiment (SHARE) 2012 contains a set of targets specifically designed to test spectral unmixing algorithms. In this paper we explore the performance of an unconstrained and three constrained least squares methods for supervised spectral unmixing. Each of the three methods provides an estimate of the abundance of known targets which can be used for detection, classification and quantification. A detailed evaluation of these spectral unmixing techniques on the SHARE 2012 hyperspectral data is used to demonstrate the performance of each method at supervised target detection, classification and quantification.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Daniel C. Heinz, Thomas Bahr, and Greg Terrie "Supervised unconstrained and constrained least squares unmixing in hyperspectral imagery", Proc. SPIE 11727, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXVII, 1172710 (12 April 2021);

Back to Top