Video-Based Automatic Target Recognition

Abstract

We present an approach for vehicle classification in IR video sequences by integrating detection, tracking and recognition. The method has two steps. First, the moving target is automatically detected using a detection algorithm. Next, we perform simultaneous tracking and recognition using an appearance-model based particle filter. The tracking result is evaluated at each frame. Low confidence in tracking performance initiates a new cycle of detection, tracking and classification. We demonstrate the robustness of the proposed method using outdoor IR video sequences.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2004
Accession Number
ADA431617

Entities

People

  • Hao Wu
  • Qinfen Zheng
  • Rama Chellappa
  • S. K. Zhou
  • Xue Mei

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Aspect Ratio
  • Automatic
  • Classification
  • Computer Vision
  • Detection
  • Equations
  • Information Science
  • Moving Targets
  • Neural Networks
  • Object Recognition
  • Probability
  • Recognition
  • Sequential Monte Carlo Methods
  • Target Recognition

Fields of Study

  • Computer science

Readers

  • Instructional Design and Training Evaluation.
  • Sensor Fusion and Tracking Systems.