Dispersion Index Based Endmember Extraction for Hyperspectral Unmixing

Abstract

In the remotely sensed hyperspectral image, separating pure materials from the mixed pixels and estimating the abundances of each material in the mixing is called hyperspectral unmixing. Hyperspectral unmixing is executed broadly in three steps. The first step is subspace identification which finds the number of endmembers present in the hyperspectral data. The second step is endmember extraction which extracts materials from the data. The last step is abundance estimation which estimates the proportions of each material in the mixing. In these three steps, endmember extraction is very challenging. As per the literature available for endmember extraction, many researchers have used convex geometry to address the endmember extraction. A novel algorithm, Dispersion Index based Endmember Extraction (DIEE) is proposed which applies convex geometry based on the Dispersion Index in this paper. The DIEE algorithm is compared with prevailing algorithms on a real and simulated dataset. It is observed from the simulation that the proposed algorithm is giving a worthy performance on both real datasets and a noisy simulated dataset.

Keywords:

• Convex geometry
• Dispersion index
• Endmember extraction
• Hyperspectral image
• Unmixing

ACKNOWLEDGEMENTS

This study was supported by the Visvesvaraya PhD scheme of the Government of India with a unique awardee number MEITY-PHD-2023. The authors of this paper gratefully thank the management of Nirma University for providing the necessary infrastructure and support.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the Visvesvaraya PhD scheme, Government of India [grant number MEITY-PHD-2023].

Notes on contributors

Dharambhai Shah

Dharambhai Shah is a research scholar in Electronics and Communication Engineering Department at Institute of Technology, Nirma University, Ahmedabad, Gujarat, India. His area of research is in machine learning, remote sensing and video processing.

Tanish Zaveri

Tanish Zaveri is a professor in Electronics and Communication Engineering Department at Institute of Technology, Nirma University, Ahmedabad, Gujarat, India. His area of research is in image processing, remote sensing and signal processing. Email: [email protected]