Camera Distance from Face Images.

We present a method for estimating the distance between a camera and a human head in 2D images from a calibrated camera. Leading head pose estimation algorithms focus mainly on head orientation (yaw, pitch, and roll) and translations perpendicular to the camera principal axis. Our contribution is a system that can estimate head pose under large translations parallel to the camera's principal axis. Our method uses a set of exemplar 3D human heads to estimate the distance between a camera and a previously unseen head. The distance is estimated by solving for the camera pose using Effective Perspective n-Point (EPnP). We present promising experimental results using the Texas 3D Face Recognition Database.