Location-guided Head Pose Estimation for Fisheye Image

Abstract--Camera with a fisheye or ultra-wide lens covers a wide field of view that cannot be modeled by the perspective projection. Serious fisheye lens distortion in the peripheral region of the image leads to degraded performance of the existing head pose estimation models trained on undistorted images. This paper presents a new approach for head pose estimation that uses the knowledge of head location in the image to reduce the negative effect of fisheye distortion. We develop an end-to-end convolutional neural network to estimate the head pose with the multi-task learning of head pose and head location. This distortion nature of the fisheye camera makes estimating head pose from fisheye image a very challenging task. HE goal of head pose estimation (HPE) in the context of computer vision is to estimate the orientation of the Head pose estimation from rectilinear image has already head concerning the camera coordinate system. The estimated achieved promising results. An intuitive idea for estimating head pose is usually expressed by Euler angles (pitch, yaw, the head pose from fisheye image is the so-called two-stage roll) [1].