본문 바로가기
  • Home

3D Pointing for Effective Hand Mouse in Depth Image

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2014, 19(8), pp.35-44
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

주성일 1 원선희 1 HYUNG IL CHOI 1

1숭실대학교

Accredited

ABSTRACT

This paper proposes a 3D pointing interface that is designed for the efficient application of ahand mouse. The proposed method uses depth images to secure high-quality results even inresponse to changes in lighting and environmental conditions and uses the normal vector of thepalm of the hand to perform 3D pointing. First, the hand region is detected and tracked using theexisting conventional method; based on the information thus obtained, the region of the palm ispredicted and the region of interest is obtained. Once the region of interest has been identified,this region is approximated by the plane equation and the normal vector is extracted. Next, toensure stable control, interpolation is performed using the extracted normal vector and the intersection point is detected. For stability and efficiency, the dynamic weight using the sigmoidfunction is applied to the above detected intersection point, and finally, this is converted into the2D coordinate system. This paper explains the methods of detecting the region of interest and thedirection vector and proposes a method of interpolating and applying the dynamic weight in orderto stabilize control. Lastly, qualitative and quantitative analyses are performed on the proposed3D pointing method to verify its ability to deliver stable control.

Citation status

* References for papers published after 2022 are currently being built.