Sparse-MVRVMs Tree for Fast and Accurate Head Pose Estimation in the Wild

摘要

Head pose estimation is an important problem in the field of computer vision and facial analysis. We model the problem of head pose estimation as a regression problem, where the three rotation angles (yaw, pitch, roll) are functions of the face appearance. We make use of that fact and learn the appearance of the face using a tree cascade of sparse Multivariate Relevance Vector Machines (MVRVM). Our method is fast and suitable for real-time applications as it is not computationally expensive. Our method learns the face appearance to estimate the head rotation angles. We evaluated our approach on two challenging datasets, the YouTube Faces and the Point and Shoot Challenging (PaSC) dataset. We achieved results of head pose estimation (yaw, pitch, roll) with mean error less than 5o and with error tolerance less than ±4 on the PaSC dataset. In terms of speed, one prediction takes around 6 milliseconds, which is suitable for real-time applications and also with high frame rate.