An Iterative Method for Hyperspectral Pixel Unmixing Leveraging Latent Dirichlet Variational Autoencoder

• Published in: IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium pp. 7527 - 7530
• Main Authors: Mantripragada, Kiran, Adler, Paul R., Olsen, Peder A., Qureshi, Faisal Z.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.07.2023
• Subjects: Estimation; Geoscience and remote sensing; Hyperspectral Unmixing; Image segmentation; Indexes; Iterative Method; Iterative methods; Latent Dirichlet Variational Autoencoder; Soil; Training data
• ISSN: 2153-7003
• DOI: 10.1109/IGARSS52108.2023.10282175

We develop a hyperspectral pixel unmixing method that uses a Latent Variational Autoencoder within an analysis-synthesis loop to (1) construct pure spectra of the materials present in an image and (2) infer the mixing ratios of these materials in hyperspectral pixels without the need of labelled data. On OnTech-HIS-Syn-6em synthetic dataset that contains pixel unmixing groundtruth, the proposed method achieves acc = 100%, SAD = 0.0582 and RMSE = 0.0695 for segmentation, endmember extraction and abundance estimation, respectively. On HYDICE Urban benchmark, the proposed method achieves acc = 72.4%, SAD = 0.1669 and RMSE = 0.1984 for segmentation, endmember extraction and abundance estimation, respectively. Additionally, we applied this technique for crop analysis on hyperspectral data collected by the United States Department of Agriculture and achieved a coefficient of determination R 2 = 0.7 with respect to the ground truth. These results confirm that the proposed method is able to perform pixel unmixing without using labelled data.