Progress Report on the Project Automatic Target Recognition (N94-124).

Abstract

Filtering, prediction and smoothing (FPS) are the three basic components of the data assimilation process in target tracking. An analytical solution of the FPS problem is possible only in a handful of particular cases, the most important of which is linear. In this case the solution is given by the Kalman filter. However, in many important cases, such as passive sonar, radar warning systems, infrared search and track, the systems are generically nonlinear. To date, the extended Kalman filter (EKF) has been the dominant algorithm technology in real-time estimation, tracking, and similar applications. A major reason for its success has been the fact that it has offered a reasonable compromise between real-time operation and satisfactory performance in some nonlinear problems. On the other hand, the EKF is a completely heuristic algorithm, requires readjustment to each particular problem, and is unstable in nonlinear problems which involve jumps, maneuvers, etc.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1997
Accession Number
ADA328926

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Computational Complexity
  • Computer Graphics
  • Computer Programs
  • Convection
  • Difference Equations
  • Differential Equations
  • Equations
  • Fokker Planck Equations
  • Kalman Filters
  • Mathematical Filters
  • Target Recognition
  • Target Tracking
  • Three Dimensional
  • Two Dimensional
  • Warning Systems

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Sensor Fusion and Tracking Systems.