Facial features tracking is an important research area in computer vision and intelligent systems which is more challenging than face tracking. Facial feature tracking has many applications such as gaze detection, teleconferencing, surveillance, model-based coding, and Human-Computer Interaction (HCI). Since there are many non-rigid motions in facial features, using particle filter could be an effective method for facial feature tracking. One drawback of particle filtering is that as the dimension of the state space increases, a large number of particles that are propagated from the previous time are wasted in area where they have low observation probability, hence a very large number of particles are necessary to track the state. As a result, the complexity increases and the speed of algorithm reduces. Auxiliary particle filter with factorized likelihood can be used to overcome this problem. In a tracking approach, the estimated state is updated by incorporating the new observations. Therefore an observation model is needed. In this lecture, a color-based observation model that is invariant to changes in illumination intensity would be discussed. The proposed observation model employs the Bhattacharyya distance to update a prior distribution calculated by the particle filter. Experimental results show that the proposed algorithm clearly outperforms the modified auxiliary particle filtering method.
Facial Features Tracking
In der Regel sind die Vorträge Teil von Lehrveranstaltungsreihen der Universität Bremen und nicht frei zugänglich. Bei Interesse wird um Rücksprache mit dem Sekretariat unter sek-ric(at)dfki.de gebeten.