Research On Single Image-Based Low Complexity Head Pose Estimation Algorithm And Its Application

Head pose can reflect important facial information,including face orientation.eye gaze direction,and even human's thinking consciousness.Although it seems to be an explicit specification of a vision task,head pose estimation has a variety of interpretations.Shortlyspeaking,head pose estimation is to identify a head in one of a few discrete orientations,e.g.,a frontal versus left/right profile view.Specifically,head pose estimate can be thought as a continuous angular measurement operation across multiple degrees of freedom(DOF).In this paper,head pose estimation is the procedure of inferring the orientation of a human head from digital images.It requires a series of processing steps to transform a pixel-based representation of a head into a high-level semantic of direction.Head pose estimation plays a vital role in various applications,e.g.,driver-assistance systems,human-computer interaction,virtual reality technology,and so on.At present,head pose estimation can be divided into two methods:geometry model-based methods and supervised learning-based methods.In this paper,we propose a novel geometry-based algorithm for accurately estimating the head pose from a single 2D facial image at a very low computational cost.Specifically,the rectangular coordinates of only four non-coplanar feature points from a predefined 3D facial model as well as the corresponding ones automatically/manually extracted from a 2D facial image are first normalized to exclude the effect of external factors(i.e.,scale factor and translation parameters).Then,the four normalized 3D feature points are represented in spherical coordinates with reference to the uniquely determined sphere by themselves,which are further iteratively refined via 3D morphing to adapt various individuals.Finally.the rotation matrix indicating the head pose is obtained by minimizing the Euclidean distance between the normalized 2D feature points and the 2D re-projections of morphed 3D feature points.Comprehensive experimental results over two popular databases,i.e.,Pointing'04 and Biwi Kinect,demonstrate that the proposed algorithm can estimate head poses with higher accuracy and lower run time than state-of-the-art geometry-based methods.Even compared with start-of-the-art learning-based methods that require large amounts of training data and computational resources or geometry based methods with additional depth information,our algorithm still produces comparable performance.