Driver’s Head Behavior Detection Using Binocular Infrared Camera

Abstract

Driver’s head behavior detection is very important for safe driving and smart driving. It can be judged based on changes in driver’s head pose. In this paper, we propose a driver's head pose estimation method based on binocular infrared camera. The head coordinate system can be established by combining two-dimensional image feature point information and three-dimensional point cloud information. With the camera coordinate system as a reference, the pose of the head coordinate system is obtained in real time, which indicate the driver's head pose. The experiments of head rotation are conducted in a real vehicle environment, and the results show that the proposed method can effectively detect driver's head behavior.