Adaptive Visual Tracking Using Particle Filter

Abstract

The difficulty in visual tracking is how to estimate the object position quickly and reliably. Particle filter (PF) has proven successfully for nonlinear non-Gaussian estimate problems, but its degeneracy problem is very serious. For alleviating the degeneracy problem of the PF, the choice of proposal distribution plays an important role. Therefore in the context, the Galerkin's method is utilized to generate the proposal distribution of the PF. It not only overcomes the degeneracy problem of the common PF algorithm, but estimation precision is better. The article also proposes the integration of color cues and shape cues adoptively into the frame. Experimental results show the feasibility of the proposed algorithm in this paper.