Abstract
This paper describes the vision-based system to track road signs from within a moving vehicle. Traffic signs located in the previous frame are tracked through image sequences using Particle filter. Particle filter has attracted much attention due to their robust tracking performance in cluttered environments. Particle filter maintains multiple hypotheses simultaneously and uses a probabilistic motion model to predict the position of the moving object. This paper uses Parzen window for estimating a probabilistic density function in Particle filter. The experimental results demonstrate that the proposed method performs well in tracking road signs present in complex scenes and various conditions.
