3D Head Tracking and Facial Expression Recovery using an Anthropometric Muscle-based Active Appearance Model

This paper describes a novel 3D model-based tracking algorithm allowing real-time recovery of 3D position, orientation and facial expressions of a moving head. The method uses a 3D anthropometric muscle-based active appearance model (3D AMB AAM), a feature-based matching algorithm, and an extended Kalman filter (EKF) pose and expression estimator. Our model is an extension of the classical 2D AAM, and uses a generic 3D wireframe model of the face, based on two sets of controls: the anatomically motivated muscle actuators to model facial expressions and statistically-based anthropometrical controls to model different facial types.