Markerless 3D Head Pose and Facial Expression Tracking

LUCAS D. TERISSI, JUAN C. GÓMEZ

Mar del Plata, Argentina

Simposio; Simposio Argentino de Inteligencia Artificial (ASAI 2009); 2009

SADIO

In this paper, novel markerless 3D head pose and facial expression tracking algorithms, based on monocular image sequences (single camera), are presented. The proposed method is based on a combination of feature-based and model-based approaches for pose estimation. A generic 3D face model, which can be adapted to any person, is used for the tracking. In contrast to other methods in the literature, the proposed method does not require a training stage. It only requires an image of the person´s face to be tracked facing to which the model is fitted manually through a graphical user interface. To evaluate the performance of the algorithms a video database was compiled. Simulation results show that the proposed tracking algorithms correctly estimate the head pose and facial expression, even when occlusions, changes in the distance to the camera and presence of other persons in the scene, occur. Although the implementation of the algorithms was not optimized for speed, they run near real time.