This paper proposes an adaptive Kalman filter (AKF) to improve the performance\nof a vision-based human machine interface (HMI) applied to a video game. The HMI identifies\nhead gestures and decodes them into corresponding commands. Face detection and feature tracking\nalgorithms are used to detect optical flow produced by head gestures. Such approaches often fail due\nto changes in head posture, occlusion and varying illumination. The adaptive Kalman filter is applied\nto estimate motion information and reduce the effect of missing frames in a real-time application.\nFailure in head gesture tracking eventually leads to malfunctioning game control, reducing the scores\nachieved, so the performance of the proposed vision-based HMI is examined using a game scoring\nmechanism. The experimental results show that the proposed interface has a good response time,\nand the adaptive Kalman filter improves the game scores by ten percent.
Loading....