Object Tracking Based on Fuzzy Information Employing a Particle Filter Algorithm

In this article, we present a new algorithm to track a moving object based on fuzzy histogram information employing a particle filter algorithm. Recently a particle filter has been proven very successful for nonlinear and non-Gaussian estimation problems. It approximates a posterior probability density of the state, such as the object position, by using samples which are called particles. Also, a fuzzy method of color and edge histograms is used. For likelihood, we consider the similarity between the fuzzy histograms of the tracked object and the region around the position of each particle with a Stochastic feature Fusion Scheme. The Bhattacharya distance is used to measure this similarity. The mean state of the particles is treated as the estimated position of the object. The experiment shows that the proposed method has strong tracking robustness and can effectively solve this problem.