Wireless Mobile Communication and Healthcare. 6th International Conference, MobiHealth 2016, Milan, Italy, November 14-16, 2016, Proceedings

Research Article

Synergy-Driven Performance Enhancement of Vision-Based 3D Hand Pose Reconstruction

Download
136 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-58877-3_42,
        author={Simone Ciotti and Edoardo Battaglia and Iason Oikonomidis and Alexandros Makris and Aggeliki Tsoli and Antonio Bicchi and Antonis Argyros and Matteo Bianchi},
        title={Synergy-Driven Performance Enhancement of Vision-Based 3D Hand Pose Reconstruction},
        proceedings={Wireless Mobile Communication and Healthcare. 6th International Conference, MobiHealth 2016, Milan, Italy, November 14-16, 2016, Proceedings},
        proceedings_a={MOBIHEALTH},
        year={2017},
        month={6},
        keywords={},
        doi={10.1007/978-3-319-58877-3_42}
    }
    
  • Simone Ciotti
    Edoardo Battaglia
    Iason Oikonomidis
    Alexandros Makris
    Aggeliki Tsoli
    Antonio Bicchi
    Antonis Argyros
    Matteo Bianchi
    Year: 2017
    Synergy-Driven Performance Enhancement of Vision-Based 3D Hand Pose Reconstruction
    MOBIHEALTH
    Springer
    DOI: 10.1007/978-3-319-58877-3_42
Simone Ciotti,*, Edoardo Battaglia1,*, Iason Oikonomidis2,*, Alexandros Makris2,*, Aggeliki Tsoli2,*, Antonio Bicchi,*, Antonis Argyros2,*, Matteo Bianchi1,*
  • 1: University of Pisa
  • 2: Foundation for Research and Technology, Hellas
*Contact email: simone.ciotti@centropiaggio.unipi.it, e.battaglia@centropiaggio.unipi.it, oikonom@ics.forth.gr, amakris@ics.forth.gr, aggeliki@ics.forth.gr, bicchi@centropiaggio.unipi.it, argyros@ics.forth.gr, matteo.bianchi@centropiaggio.unipi.it

Abstract

In this work we propose, for the first time, to improve the performance of a Hand Pose Reconstruction (HPR) technique from RGBD camera data, which is affected by self-occlusions, leveraging upon , i.e., information on how human most commonly use and shape their hands in everyday life tasks. More specifically, in our approach, we ignore joint angle values estimated with low confidence through a vision-based HPR technique and fuse synergistic information with such incomplete measures. Preliminary experiments are reported showing the effectiveness of the proposed integration.