Deep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis
This addresses the issue of inadequate spectral library diversity for remote sensing practitioners, though it is an incremental improvement over existing MESMA methods.
The paper tackled the problem of small spectral libraries limiting Multiple Endmember Spectral Mixture Analysis (MESMA) performance by proposing a deep generative model-based library augmentation strategy, which improved spectral unmixing quality in experiments with synthetic and real data.
Multiple Endmember Spectral Mixture Analysis (MESMA) is one of the leading approaches to perform spectral unmixing (SU) considering variability of the endmembers (EMs). It represents each EM in the image using libraries of spectral signatures acquired a priori. However, existing spectral libraries are often small and unable to properly capture the variability of each EM in practical scenes, which compromises the performance of MESMA. In this paper, we propose a library augmentation strategy to increase the diversity of existing spectral libraries, thus improving their ability to represent the materials in real images. First, we leverage the power of deep generative models to learn the statistical distribution of the EMs based on the spectral signatures available in the existing libraries. Afterwards, new samples can be drawn from the learned EM distributions and used to augment the spectral libraries, improving the overall quality of the SU process. Experimental results using synthetic and real data attest the superior performance of the proposed method even under library mismatch conditions.