EAI Endorsed Transactions on Creative Technologies 15(3): e2

Research Article

Head pose estimation & TV Context: current technology

Download65 downloads
  • @ARTICLE{10.4108/ct.2.3.e2,
        author={Francois Rocca and Matei Mancas and Fabien Grisard and Julien Leroy and Thierry Ravet and Bernard Gosselin},
        title={Head pose estimation \& TV Context: current technology},
        journal={EAI Endorsed Transactions on Creative Technologies},
        volume={15},
        number={3},
        publisher={ICST},
        journal_a={CT},
        year={2015},
        month={6},
        keywords={head pose estimation, viewer interest, face direction, Qualisys, Kinect, face tracking, 3D point cloud},
        doi={10.4108/ct.2.3.e2}
    }
    
  • Francois Rocca
    Matei Mancas
    Fabien Grisard
    Julien Leroy
    Thierry Ravet
    Bernard Gosselin
    Year: 2015
    Head pose estimation & TV Context: current technology
    CT
    ICST
    DOI: 10.4108/ct.2.3.e2
Francois Rocca1,*, Matei Mancas1, Fabien Grisard1, Julien Leroy1, Thierry Ravet1, Bernard Gosselin1
  • 1: University of Mons (UMONS), Faculty of Engineering (FPMs), 20, Place du Parc, 7000 Mons, Belgium
*Contact email: francois.rocca@umons.ac.be

Abstract

With the arrival of low-cost high quality cameras, implicit user behaviour tracking is easier and it becomes very interesting for viewer modelling and content personalization in a TV context. In this paper, we present a comparison between three common algorithms of automatic head direction extraction for a person watching TV in a realistic context. Those algorithms compute the different rotation angles of the head (pitch, roll, yaw) in a non-invasive and continuous way based on 2D and/or 3D features acquired with low cost cameras. These results are compared with a reference based on the Qualisys motion capture commercial system which is a robust marker-based tracking system. The performances of the different algorithms are compared function of different configurations. While our results show that full implicit behaviour tracking in real-life TV setups is still a challenge, with the arrival of next generation sensors (as the new Kinect one sensor), accurate TV personalization based on implicit behaviour is close to become a very interesting option.