Kalman Filter

Definition

The Kalman filter—and its nonlinear variants EKF and UKF—fuses noisy measurements with a process model to maintain a probabilistic estimate of system state. It is the most widely used estimator for tracking, navigation, and target localization on CCA platforms and underlies most multi-sensor fusion stacks.

Reference attributes

Variants

KF, EKF, UKF, square-root forms

Use cases

INS/GPS, target tracking, sensor fusion

Related terms

• Multiple Hypothesis Tracking (MHT)
  Tracking algorithm that maintains parallel hypotheses about data association.
• Particle Filter
  Sequential Monte Carlo estimator for nonlinear, non-Gaussian state estimation.