This paper proposes an annealed particle swarm optimization based particle filter algorithm for articulated 3D human body tracking. In our algorithm, a sampling covariance and an annealing factor are incorporated into the velocity updating equation of particle swarm optimization (PSO). The sampling covariance and the annealing factor are initiated with appropriate values at the beginning of the PSO iteration, and `annealing' is carried out at reasonable steps. Experiments with multi-camera walking sequences from the Brown dataset show that: 1) the proposed tracker can effectively alleviate the problem of inconsistency between the image likelihood and the true model; 2) the tracker is also robust to noise and body self-occlusion.