Sensor Fusion Algorithms and Performance Limits

Abstract

The concealed weapons detection program involves auto-detection and recognition of weapons under clothing. Single sensor methods are insufficient for detection in many situations. This program develops methodologies for detecting weapons under clothing using multiple dissimilar imaging sensors. Several signal processing steps are considered starting with image acquisition and concluding with a binary or tertiary decision about the presence or absence of a weapon. Image registration, noise removal filtering, image fusion and shape recognition are all discussed. Individual attributes are used to register images which are then fused in the wavelet domain.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2001
Accession Number
ADA391935

Entities

People

  • Hua-mei Chen
  • Liane C. Ramac
  • Mucahit K. Uner
  • Pramod Varshney

Organizations

  • Syracuse University

Tags

Communities of Interest

  • Biomedical
  • Engineered Resilient Systems
  • Materials and Manufacturing Processes
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Automata Theory
  • Clothing
  • Computational Science
  • Computer Vision
  • Data Compression
  • Detection
  • Detectors
  • Electrical Engineering
  • Image Processing
  • Image Registration
  • Information Processing
  • Information Science
  • Pattern Recognition
  • Sensor Fusion
  • Signal Processing

Readers

  • Image Processing and Computer Vision.
  • Sensor Fusion and Tracking Systems.
  • Systems Analysis and Design