Automated Construction of Multiple Regional Libraries for Neighborhoodwise Local Multiple Endmember Unmixing

Endmember variability has been recognized as a major source of error in spectral unmixing. Although numerous unmixing algorithms have been developed, there is a gap between the studies emphasizing automated processing and those focusing on estimation accuracy. Endmember variability is rarely considered in most automated processing approaches, while existing unmixing algorithms that accommodate endmember variability partially rely on human involvement. To fill this gap, an automated unmixing chain prototype is proposed in this research, which integrates endmember extraction, refinement, and multiple endmember spectral mixture analysis (MESMA). In particular, this prototype is designed to automate three processing steps with intelligent approaches, including optimal size determination to generate neighborhoods as a spatial constraint, endmember refinement to select representative endmembers in spectral libraries, and automated construction of multiple regional libraries. Based on this prototype, three specific local and global MESMA variants with different neighborhood types were implemented, and their performances to estimate urban impervious surface abundance were compared. Analyses indicate three major conclusions. First, by examining spatial dependence of endmember spectra, an optimal neighborhood size can be obtained, with which a localized neighborhood can be derived by aggregating spatially close image segments. Second, by applying spatial and iterative K-means spectral clustering to endmembers from the identified neighborhoods, parsimonious and representative endmembers can be refined from a large endmember pool. Accordingly, a local spectral library can be automatically constructed in each neighborhood. Third, neighborhoodwise object-based MESMA (NEW OB-MESMA) significantly outperforms the other two MESMA variants with improved estimation accuracy and increased computational efficiency.