Sparse modeling for hyperspectral imagery with LiDAR data fusion for subpixel mapping

Conference Paper

Several studies suggest that the use of geometric features along with spectral information improves the classification and visualization quality of hyperspectral imagery. These studies normally make use of spatial neighborhoods of hyperspectral pixels for extracting these geometric features. In this work, we merge point cloud Light Detection and Ranging (LiDAR) data and hyperspectral imagery (HSI) into a single sparse modeling pipeline for subpixel mapping and classification. The model accounts for material variability and noise by using learned dictionaries that act as spectral endmembers. Additionally, the estimated abundances are influenced by the LiDAR point cloud density, particularly helpful in spectral mixtures involving partial occlusions and illumination changes caused by elevation differences. We demonstrate the advantages of the proposed algorithm with co-registered LiDAR-HSI data. © 2012 IEEE.

Full Text

Duke Authors

Cited Authors

  • Castrodad, A; Khuon, T; Rand, R; Sapiro, G

Published Date

  • December 1, 2012

Published In

  • International Geoscience and Remote Sensing Symposium (Igarss)

Start / End Page

  • 7275 - 7278

Digital Object Identifier (DOI)

  • 10.1109/IGARSS.2012.6351982

Citation Source

  • Scopus