Improving Background Multivariate Normality and Target Detection Performance Using Spatial and Spectral Segmentation

Abstract

Target deteetion in reflective hyperspeetral imagery generally involves the application of a spectral matched filter on a per-pixei basis to create an image of the target lihenhood of occupying each pixel. Stochastic (or unstructured) target detection tcehniques require the user to define an estimate of the background mean and covariance from which to separate out the desired targets in the image. Typically, scene-wide statistics are used, although it Is simple to show that this methodology does not produce sufficiently multivariate normal bachgrounds nor does it necessarily represent the best suppression of likely false alarms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 28, 2006
Accession Number
ADA446551

Entities

People

  • David W. Messinger
  • Jason E. West
  • John Schott

Organizations

  • Rochester Institute of Technology

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Algorithms
  • Computer Programs
  • Computer Vision
  • Data Science
  • Detection
  • Detectors
  • False Alarms
  • Information Science
  • Matched Filters
  • Military Personnel
  • Normality
  • Statistics
  • Target Detection
  • Theses
  • Warning Systems

Readers

  • Image Processing and Computer Vision.
  • Sensor Fusion and Tracking Systems.
  • Statistical inference.