Estimation and Simulation of Hyperspectral Images

Abstract

The goal of the research was to create enhanced practical methods to estimate and simulate hyperspectral images by using recorded data of low spectral resolution images. These data can be used to test algorithms designed for many hyperspectral image analysis tasks, such as target detection, classification and tracking. An advantage is that these images are unclassified and can be used in a university environment where international students are often used. The images are also readily defined to allow ground truth to be known so that accuracy of the image analysis tasks can be measured.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 23, 2009
Accession Number
ADA520615

Entities

People

  • H. J. Trussell

Organizations

  • North Carolina State University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Agreements
  • Algorithms
  • Computer Programs
  • Convex Sets
  • Department Of Defense
  • Detection
  • Distribution Functions
  • Low Resolution
  • Mathematics
  • Neural Networks
  • Probability
  • Probability Distributions
  • Random Variables
  • Simulations
  • Students
  • Target Detection

Fields of Study

  • Physics

Readers

  • Computational Modeling and Simulation
  • Defense Technology Research and Development.
  • Image Processing and Computer Vision.