A hyperspectral image analysis workbench for environmental science applications
A significant challenge to the information sciences is to provide more powerful and accessible means to exploit the enormous wealth of data available from high-resolution imaging spectrometry, or hyperspectral'' imagery, for analysis, for mapping purposes, and for input to environmental modeling applications. As an initial response to this challenge, Argonne's Advanced Computer Applications Center has developed a workstation-based prototype software workbench which employs Al techniques and other advanced approaches to deduce surface characteristics and extract features from the hyperspectral images. Among its current capabilities, the prototype system can classify pixels by abstract surface type. The classification process employs neural network analysis of inputs which include pixel spectra and a variety of processed image metrics, including image texture spectra'' derived from fractal signatures computed for subimage tiles at each wavelength.
- Research Organization:
- Argonne National Lab., IL (United States)
- Sponsoring Organization:
- USDOE; USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-31109-ENG-38
- OSTI ID:
- 6987920
- Report Number(s):
- ANL/CP-77460; CONF-930141-1; ON: DE93000603
- Resource Relation:
- Conference: 9. international conference on interactive information and processing, Anaheim, CA (United States), 17-22 Jan 1993
- Country of Publication:
- United States
- Language:
- English
Similar Records
A hyperspectral image data exploration workbench for environmental science applications
Wildfires Temperature Estimation by Complementary Use of Hyperspectral PRISMA and Thermal (ECOSTRESS & L8)
Related Subjects
54 ENVIRONMENTAL SCIENCES
SITE CHARACTERIZATION
IMAGE PROCESSING
SURFACES
COMPUTERIZED SIMULATION
FRACTALS
LAND USE
PROCESSING
SIMULATION
990200* - Mathematics & Computers
540210 - Environment
Terrestrial- Basic Studies- (1990-)