Translator Disclaimer
Paper
27 September 2006 Hyperspectral signatures of an eastern North American temperate forest
Author Affiliations +
Abstract
We describe a new approach to unsupervised classification that automatically finds dense parts of the hyperspectral data cloud. These dense regions are identified as the cluster centers required for unsupervised classification. The approach is tested using AVIRIS hyperspectral imagery from central Texas that has spectrally well separated land covers. The algorithm is then applied to the more stressing case of separating coniferous and deciduous forests in eastern Virginia. We find that the major spectral difference is brighter reflectance in the NIR plateau for deciduous forests compared to adjacent coniferous stands. This difference is sufficient to distinguish the forest types, and is confirmed by comparison to ground truth information.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
John Cipar, Ronald Lockwood, and Thomas Cooley "Hyperspectral signatures of an eastern North American temperate forest", Proc. SPIE 6298, Remote Sensing and Modeling of Ecosystems for Sustainability III, 629802 (27 September 2006); https://doi.org/10.1117/12.679056
PROCEEDINGS
10 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Skin detection in hyperspectral images
Proceedings of SPIE (May 21 2015)
Spectral LiDAR analysis for terrain classification
Proceedings of SPIE (May 05 2017)
Background spectral library for Fort A.P. Hill, Virginia
Proceedings of SPIE (November 09 2004)
Material mapping for 3D objects in hyperspectral images
Proceedings of SPIE (July 16 1999)

Back to Top