Particle Filtering with Evidential Reasoning

Abstract

Particle filtering has come into favor in the computer vision community with the CONDENSATION algorithm. Perhaps the main reason for this is that it relaxes many of the assumptions made with other tracking algorithms, such as the Kalman filter. It still places a strong requirement on the ability to model the observations and dynamics of the systems with conditional probabilities. In practice these may be hard to measure precisely, especially in situations where multiple sensors are used.

Here, a particle filtering algorithm which uses evidential reasoning is presented, which relaxes the need to be able to precisely model observations, and also provides an explicit model of ignorance.