Archetypal Analysis for Sparse Representation-based Hyperspectral Sub-pixel Quantification
This work addresses land cover quantification for environmental monitoring in urban areas, presenting an incremental improvement over existing methods.
The paper tackled the problem of estimating land cover fractions from hyperspectral remote sensing images by automatically deriving elementary spectra using archetypal analysis, showing it is an adequate and efficient alternative to manually designed spectral libraries in terms of reconstruction error, mean absolute error, and other metrics.
The estimation of land cover fractions from remote sensing images is a frequently used indicator of the environmental quality. This paper focuses on the quantification of land cover fractions in an urban area of Berlin, Germany, using simulated hyperspectral EnMAP data with a spatial resolution of 30m$\times$30m. We use constrained sparse representation, where each pixel with unknown surface characteristics is expressed by a weighted linear combination of elementary spectra with known land cover class. We automatically determine the elementary spectra from image reference data using archetypal analysis by simplex volume maximization, and combine it with reversible jump Markov chain Monte Carlo method. In our experiments, the estimation of the automatically derived elementary spectra is compared to the estimation obtained by a manually designed spectral library by means of reconstruction error, mean absolute error of the fraction estimates, sum of fractions, $R^2$, and the number of used elementary spectra. The experiments show that a collection of archetypes can be an adequate and efficient alternative to the manually designed spectral library with respect to the mentioned criteria.