The evaluation of the Gaussian Mixture Probability Hypothesis Density approach for multi-target tracking

This paper describes the performance of the Gaussian Mixture Probability Hypothesis Density (GM-PHD) filter for multiple human tracking in an intelligent vision system. Human movement trajectories were observed with a camera and tracked by the GM-PHD filter. The filter multi-target tracking ability was validated by two random motion trajectories in the paper. To evaluate the filter performance in relation to the target movement, the motion velocity and angular velocity as key evaluation factors were proposed. A circular motion model was implemented for simplified analysis of the filter tracking performance. The results indicate that the mean absolute error defined as the difference between the filter prediction and the ground truth is proportional to the motion speed and angular velocity of the target. The error is only slightly affected by the tracking targets´ number.