MiSiSUn: Minimum Simplex Semisupervised Unmixing
This work addresses a domain-specific problem in remote sensing or signal processing for unmixing data, representing an incremental advancement with a novel method for a known bottleneck.
The paper tackles the problem of semisupervised geometric unmixing by incorporating data geometry into library-based methods, resulting in performance improvements of 1 dB to over 3 dB compared to state-of-the-art methods on simulated datasets and close visual alignment with geological maps on real data.
This paper proposes a semisupervised geometric unmixing approach called minimum simplex semisupervised unmixing (MiSiSUn). The geometry of the data was incorporated for the first time into library-based unmixing using a simplex-volume-flavored penalty based on an archetypal analysis-type linear model. The experimental results were performed on two simulated datasets considering different levels of mixing ratios and spatial instruction at varying input noise. MiSiSUn considerably outperforms state-of-the-art semisupervised unmixing methods. The improvements vary from 1 dB to over 3 dB in different scenarios. The proposed method was also applied to a real dataset where visual interpretation is close to the geological map. MiSiSUn was implemented using PyTorch, which is open-source and available at https://github.com/BehnoodRasti/MiSiSUn. Moreover, we provide a dedicated Python package for Semisupervised Unmixing, which is open-source and includes all the methods used in the experiments for the sake of reproducibility.