Recent Advances in Spectral Unmixing for Hyperspectral Imagery
April 6, 2022 @ 10:00 am - 11:00 am +04
Hyperspectral imaging (HSI) systems collect image data simultaneously in hundreds of narrow, adjacent spectral bands. Hyperspectral remote sensing is used in a wide array of applications such as agriculture, mineralogy, surveillance, etc.In HSI, the observed radiation represented from a single pixel rarely comes from a pure material. However, the high spectral resolution of the HSI spectrometer enables the detection, identification and classification of subpixel objects and their contribution to the measured spectra. The distinct materials associated with the surface are called endmembers, and the fractions in which they appear in a pixel are called abundances. The unmixing problem refers to finding the number of endmembers, their spectral signatures, and their abundances from a given hyperspectral image.