Automatic face tracking system using quadrotors: Control by goal position thresholding

This paper proposes a human face tracking system for obtaining elderly people´s facial images, which can be used to estimate their individual emotion. Quadrotors are used to overcome occlusion and obtain closer facial images, while Kinect sensors provide human detection and quadrotor navigation. Noise from the measured head position results in vibration of the goal position, and subsequently the quadrotor, which can cause blurred images and safety problem. In order to improve the stability of the quadrotor, we propose an algorithm using threshold to fix the quadrotor´s goal position. Performance of the algorithm is evaluated by using the detected positions of the quadrotor and is compared with tracking without threshold algorithm, as well as with different threshold values. Based on these positions, face tracking results are also calculated by simulating projection of the face in real world onto the image plane and evaluating the quality of the obtained face.