Robust Head Pose Estimation Using Extreme Gradient Boosting Machine on Stacked Autoencoders Neural Network

Abstract

Head pose estimation is an important sign in helping robots and other intelligence machines understand human. It plays a vital role in designing human computer interaction systems because many applications rely on precise results of head pose angles such as human behavior analysis, gaze estimation, 3D head reconstruction etc. This study presents a robust approach for estimating the head pose angles in a single image. More specifically, the proposed system first encodes the global features extracted from Histogram of Oriented Gradients in a multi stacked autoencoders neural network. Based on the hidden nodes in deep layers, Autoencoder has been proposed for feature reduction while maintaining the key information of data. A scalable gradient boosting machine is then employed to train and classify the embedded features. Experiences have evaluated on the Pointing 04 dataset and show that the proposed approach outperforms the state-of-the-art methods with the low head pose angle errors in pitch and yaw as 6.16° and 7.17°, respectively.