Teacher Attention Measurement Based on Head Pose Estimation

Teachers’ attention plays an important role in guiding students’ attention and communicating with students. It is a challenging task to measure teachers’ attention non intrusively. This paper first gives the definition of this task, and proposes a specific method to measure teachers’ attention in a given video based on head pose estimation. This method obtains the head posture information by inputting the head image information in the video into the Hopenet, determines the gaze point constant based on the tangent function of the pitch angle, and calculates the teacher’s attention based on the line of gaze and the gaze point range. The experimental results show that the method has high accuracy and is close to human recognition level.