• DocumentCode
    651109
  • Title

    Appearance-based gaze estimation using kinect

  • Author

    Jinsoo Choi ; Byungtae Ahn ; Jaesik Parl ; In So Kweon

  • Author_Institution
    Korea Adv. Inst. of Sci. & Technol., Daejeon, South Korea
  • fYear
    2013
  • fDate
    Oct. 30 2013-Nov. 2 2013
  • Firstpage
    260
  • Lastpage
    261
  • Abstract
    Human gaze tracking has gathered much attention due to its capability to detect intuitive attention. Appearance-based methods can work with a single camera in ordinary conditions to track human gaze. An effective way to generate eye appearances is proposed using the Kinect. The head pose information is obtained from the Kinect after a series of calibrations. The Eye Appearance features are collected through ASM and KLT feature tracker. With 23 training samples, the error is found to be 1.07°. This paper proposes an efficient scheme for gaze tracking using a single Kinect device.
  • Keywords
    feature extraction; object tracking; sensors; shape recognition; ASM feature tracker; KLT feature tracker; Kinect device; active shape model; appearance-based gaze estimation; eye appearance features; head pose information; human gaze tracking; List keywords here. No more than 5;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Ubiquitous Robots and Ambient Intelligence (URAI), 2013 10th International Conference on
  • Conference_Location
    Jeju
  • Print_ISBN
    978-1-4799-1195-0
  • Type

    conf

  • DOI
    10.1109/URAI.2013.6677362
  • Filename
    6677362