Translator Disclaimer
20 August 2001 Gibbs-based unsupervised segmentation approach to partitioning hyperspectral imagery for terrain applications
Author Affiliations +
Abstract
A Gibbs-based approach to partitioning hyperspectral imagery into homogeneous regions is investigated for terrain mapping applications. The form of Bayesian estimation, Maximum A Posteriori (MAP) estimation, is applied through the use of a Gibbs distribution defined over a neighborhood system and is implemented as a multi-grid process. Appropriate energy functions and neighborhood graph structures are investigated, which model spectral disparities in an image using spectral angle and/or Euclidean distance. Experiments are conducted on a HYDICE scene collected over an area adjacent to Fort Hood, Texas, that contains a diverse range of terrain features and that is supported with ground truth. Suitable parameter ranges are investigated, and the behavior of the algorithm is characterized using individual and combined measures of disparity within the context of a more general framework, one that supports mixed-pixel processing.
© (2001) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Robert S. Rand and Daniel M. Keenan "Gibbs-based unsupervised segmentation approach to partitioning hyperspectral imagery for terrain applications", Proc. SPIE 4381, Algorithms for Multispectral, Hyperspectral, and Ultraspectral Imagery VII, (20 August 2001); https://doi.org/10.1117/12.437018
PROCEEDINGS
11 PAGES


SHARE
Advertisement
Advertisement
Back to Top