DOI QR코드

DOI QR Code

The Estimation of Hand Pose Based on Mean-Shift Tracking Using the Fusion of Color and Depth Information for Marker-less Augmented Reality

비마커 증강현실을 위한 색상 및 깊이 정보를 융합한 Mean-Shift 추적 기반 손 자세의 추정

  • Lee, Sun-Hyoung (Dept. of Electronic Engineering, Soongsil University) ;
  • Hahn, Hern-Soo (Dept. of Information Communication & Electronic Engineering, Soongsil University) ;
  • Han, Young-Joon (Dept. of Information Communication & Electronic Engineering, Soongsil University)
  • 이선형 (숭실대학교 전자공학과) ;
  • 한헌수 (숭실대학교 정보통신전자공학부) ;
  • 한영준 (숭실대학교 정보통신전자공학부)
  • Received : 2012.05.08
  • Accepted : 2012.05.29
  • Published : 2012.07.31

Abstract

This paper proposes a new method of estimating the hand pose through the Mean-Shift tracking algorithm using the fusion of color and depth information for marker-less augmented reality. On marker-less augmented reality, the most of previous studies detect the hand region using the skin color from simple experimental background. Because finger features should be detected on the hand, the hand pose that can be measured from cameras is restricted considerably. However, the proposed method can easily detect the hand pose from complex background through the new Mean-Shift tracking method using the fusion of the color and depth information from 3D sensor. The proposed method of estimating the hand pose uses the gravity point and two random points on the hand without largely constraints. The proposed Mean-Shift tracking method has about 50 pixels error less than general tracking method just using color value. The augmented reality experiment of the proposed method shows results of its performance being as good as marker based one on the complex background.

본 논문은 비마커 증강현실(Marker-less Augmented Reality)을 위한 색상 및 깊이 정보를 융합한 Mean-Shift 추적 알고리즘 기반 손 자세의 추정 기법을 제안한다. 기존 비마커 증강현실의 연구는 손을 검출하기 위해 단순한 실험 배경에서 피부색상 기반으로 손 영역을 검출한다. 그리고 손가락의 특징점을 검출하여 손의 자세를 추정하므로 카메라에서 검출할 수 있는 손 자세에 많은 제약이 따른다. 하지만, 본 논문은 3D 센서의 색상 및 깊이 정보를 융합한 Mean-Shift 추적 기법을 사용함으로써 복잡한 배경에서 손을 검출할 수 있으며 손 자세를 크게 제약하지 않고 손 영역의 중심점과 임의의 2점의 깊이 값만으로 정확한 손 자세를 추정한다. 제안하는 Mean Shift 추적 기법은 피부 색상정보만 사용하는 방법보다 약 50픽셀 이하의 거리 오차를 보였다. 그리고 증강실험에서 제안하는 손 자세 추정 방법은 복잡한 실험환경에서도 마커 기반 방법과 유사한 성능의 실험결과를 보였다.

Keywords

References

  1. Ju-Hyun Lee, "A Development Strategy of Augmented Reality Contents in the Contextual Environments," Human Contents, no.19, pp.179-218, 2010 November.
  2. Kyung-Hee Noh, Hyung-Keun Jee, Sukhyun Lim, "Effect of Augmented Reality Contents Based Instruction on Academic Achievement, Interest and Flow of Learning," Korea Contents, Vol.10, no.2, pp.1-13, 2010 February. https://doi.org/10.5392/JKCA.2010.10.2.001
  3. Keon-Hee Park, Guee-Sang Lee, "Hand Gesture Interface for Manipulating 3D Objects in Augmented Reality," Korea Contents, Vol.10, no.5, pp.20-28, 2010 May. https://doi.org/10.5392/JKCA.2010.10.5.020
  4. Y. Shen, "Vision-Based Hand Interaction in Augmented Reality Environment," International Journal of Human-Computer Interaction, vol.27, no.6, pp.523-544, May 2011. https://doi.org/10.1080/10447318.2011.555297
  5. Junchul Chun, Byungsung Lee, "Dynamic Man ipulation of a Virtual Object in Marker-less AR system Based on Both Human Hands," KSII Transactions on Internet and Information Systems, vol.4, no.4, pp.618-632, August 2010.
  6. Junyeong Choi, Hanhoon Park, Jungsik Park, and Jong-Il Park, "Implementation of Hand-Gesture Bas ed Augmented Reality Interface on Mobile Phone," The korea Society of Broadcast Engineers, Vol.16, no.6, pp.941-950, 2011 November.
  7. Z. Zhang, "Flexible Camera Calibration by Viewing a Plane from Unknown Orientations," Proc. Int'l Conf. Computer Vision, pp. 666-673, 1999.
  8. ARTOOLKIT. Human Interface Technology Laboratory, http://www.hitl.Washin gton.edu/artoolkit
  9. OpenNI. (n.d.). OpenNI documentation. http://www.openni.org/ images/ stories/ pdf /OpenNI_UserGuide_v4.pdf
  10. Rovelo, G. (n.d.). ARTOOLKIT II. from https://jira.ai2.upv.es/confluence/download/attachments/12222496/WGM18_ARToolKitII.pdf?version=1&modificationDate=1304095263000
  11. Kwangsoo Kim, Sooyoun Hong, Sooyeong Kwak, Jungho Ahn, Hyeran Byun, "Multiple Human Tracking using Mean Shift and Depth Map with a Moving Stereo Camera," The korean Institute of Ingormation Scientists and Engineers, Vol.34, no.10, pp.937-944, 2007 October.
  12. Y. Cheng, "Mean shift, mode seeking, and clustering," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.17, pp.790-799, 1995. https://doi.org/10.1109/34.400568
  13. D. Comaniciu, "Kernel-Based Object Tracking," IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 25, no. 5, May 2003.
  14. Sang-Geol Lee, Cheol-Ki Kim, Eui-Young Cha, "Retouching Method for Watercolor Painting Effect Using Mean Shift Segmentation," The Korea Society of Computer Information, Vol.15, no.9, pp.25-33, 2010 September. https://doi.org/10.9708/jksci.2010.15.9.025
  15. Heeman Lee, "Implementing Augmented Reality By Using Face Detection, Recognition And Motion Tracking," The Korea Society of Computer Information, Vol.17, no.1, pp.97-104, 2012 January. https://doi.org/10.9708/jksci.2012.17.1.097

Cited by

  1. 키넥트를 이용한 종이건반 피아노 구현 연구 vol.17, pp.12, 2012, https://doi.org/10.9708/jksci/2012.17.12.219