Particle filter in vision tracking

Abstract

The extended Kalman filter (EKF) has been used as the standard technique for performing recursive nonlinear estimation in vision tracking. In this report, we present an alternative filter with performance superior to that of the EKF. This algorithm, referred to as the Particle filter. Particle filtering was originally developed to track objects in clutter (multi-modal distribution). We present as results the filter behavior when exist objects with similar characteristic to the object to track.