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.

Additional Metadata
Keywords 3D head, Active appearance model, Anthropometric, Face analysis, Face tracking, Human computer interaction, Model-based video coding, Muscle-based
Conference 2007 IEEE Instrumentation and Measurement Technology, IMTC 2007 - Synergy of Science and Technology in Instrumentation and Measurement
Citation
Cordea, M.D. (Marius D.), Petriu, E.M. (Emil M.), & Petriu, D. (2007). 3D head tracking and facial expression recovery using an anthropometric muscle-based active appearance model. Presented at the 2007 IEEE Instrumentation and Measurement Technology, IMTC 2007 - Synergy of Science and Technology in Instrumentation and Measurement.