Nonnegative matrix factorization based feature selection analysis for hyperspectral imagery of sediment-laden riverine flow

Nicholas V. Scott; Ian C. Moore

doi:10.1117/12.2301273

25 May 2018 Nonnegative matrix factorization based feature selection analysis for hyperspectral imagery of sediment-laden riverine flow

Nicholas V. Scott, Ian C. Moore

Author Affiliations +

Proceedings Volume 10631, Ocean Sensing and Monitoring X; 1063114 (2018) https://doi.org/10.1117/12.2301273
Event: SPIE Defense + Security, 2018, Orlando, FL, United States

Abstract

Nonnegative matrix factorization-based feature selection analysis performed on land based hyperspectral imagery of the Mississippi river identifies ten spectral bands in the visible and near infrared portion of the electromagnetic spectrum that are significant contributors to the resulting structural image clustering of sediment-laden water. Different distance metrics provide clear evidence of the potency of these spectral bands for class separation of turbid, sediment-laden water from clear water, provided that the data contains low noise. In addition, feature ranking of spectral band subsets of the identified characteristic spectral bands allows insight into the relative importance of smaller spectral band subsets for water-sediment characterization. Results support present day multispectral satellite design methods for land-water imagery where payload power resources are relegated to certain spectral bands at the expense of others.

Citation Download Citation

Nicholas V. Scott and Ian C. Moore "Nonnegative matrix factorization based feature selection analysis for hyperspectral imagery of sediment-laden riverine flow ", Proc. SPIE 10631, Ocean Sensing and Monitoring X, 1063114 (25 May 2018); https://doi.org/10.1117/12.2301273

ACCESS THE FULL ARTICLE