Unmixing based Change Detection for Hyperspectral Images with Endmember Variability

摘要

Unmixing based change detection (UBCD) provides subpixel level information on the nature of the changes that occur in a temporal image series, in addition to providing a multi-output change detection map. These advantages have recently carried UBCD to prominence among change detection approaches for hyperspectral images. However, most, if not all, works on UBCD operate with the assumption that the endmembers do not vary in character temporally or locally. This assumption often fails to uphold, as intrinsic variability of endmembers is a significant concern for most real datasets, in addition to endmember variability occurring in temporal images due to changes in lighting or acquisition conditions. This paper proposes unmixing with the recently proposed extended linear mixture model (ELMM) to address spectral variability for UBCD and highlights its advantage with respect to UBCD with the linear mixture model (LMM) through experiments on synthetic and real datasets.