A New Elbow Estimation Method for Selecting the Best Solution in Sparse Unmixing

The goal of hyperspectral image analysis is often to determine which materials, out of a given set of possibilities, are present in each pixel. As hyperspectral data are being gathered in rapidly increasing amounts, automatic image analysis is becoming progressively more important. Automatic identification of materials from a mixed pixel is possible with 1) Bayesian unmixing algorithms and 2) multiobjective sparse unmixing algorithms when a method such as elbow estimation is used to select the best solution from the set of Pareto-optimal solutions. We develop a new elbow estimation method called termination condition adaptive elbow (TCAE) for selecting the best solution from the set of Pareto-optimal solutions to a biobjective unmixing problem. Specifically, the two objectives are assumed to be the sparsity level of the fractional abundance vector and the reconstruction error. We conduct experiments with real-world unmixing applications in mind, and TCAE performs significantly better than a state-of-the-art elbow estimation method when they are both used to select the best solution from the sequence of fractional abundance vectors generated by iterative spectral mixture analysis (ISMA). Furthermore, the combination of ISMA and TCAE is able to identify endmembers from mixed pixels several times faster and with higher F1-score than the two Bayesian unmixing algorithms used as a reference. We conclude that the combination of ISMA and TCAE facilitates automatic, reliable, and rapid identification of endmembers from mixed pixels.