• DocumentCode
    3080292
  • Title

    A hand-based visual intent recognition algorithm for wheelchair motion

  • Author

    Luhandjula, Thierry ; Djouani, Karim ; Hamam, Yskandar ; van Wyk, Ben ; Williams, Quentin

  • Author_Institution
    French South African Tech. Inst. in Electron., Tshwane Univ. of Technol., Pretoria, South Africa
  • fYear
    2010
  • fDate
    13-15 May 2010
  • Firstpage
    749
  • Lastpage
    756
  • Abstract
    This paper describes an algorithm for a visual human-machine interface that infers a person´s intention from the motion of the hand. Work in progress shows a proof of concept tested on static images. The context for which this solution is intended is that of wheelchair bound individuals whose intentions are the direction and speed variation of the wheelchair. Results show that the symmetry property of the hand in motion can serve as an intent indicator.
  • Keywords
    handicapped aids; human computer interaction; image motion analysis; image recognition; inference mechanisms; wheelchairs; hand-based visual intent recognition algorithm; visual human-machine interface; wheelchair motion; Collaboration; Control systems; Councils; Face detection; Humans; Infrared sensors; Magnetic heads; Man machine systems; Testing; Wheelchairs; Human-machine interface; intention; intention curves; intention detection; symmetry curves;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Human System Interactions (HSI), 2010 3rd Conference on
  • Conference_Location
    Rzeszow
  • Print_ISBN
    978-1-4244-7560-5
  • Type

    conf

  • DOI
    10.1109/HSI.2010.5514485
  • Filename
    5514485