A Particle-Filtering Approach for Vehicular Tracking Adaptive to Occlusions

Abstract

In this paper, we propose a new particle-filtering approach for handling partial and total occlusions in vehicular tracking situations. Our proposed method, which is named adaptive particle filter (APF), uses two different operation modes. When the tracked vehicle is not occluded, the APF uses a normal probability density function (pdf) to generate the new set of particles. Otherwise, when the tracked vehicle is under occlusion, the APF generates the new set of particles using a Normal-Rayleigh pdf. Our approach was designed to detect when a total occlusion starts and ends and to resume vehicle tracking after disocclusions. We have tested our APF approach in a number of traffic surveillance video sequences with encouraging results. Our proposed approach tends to be more accurate than comparable methods in the literature, and at the same time, it tends to be more robust to target occlusions.