Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Quick and accurate estimation of human 3D hand posture


We propose a three-dimensional hand posture estimation system that can retrieve a hand posture image most similar to the input data from a non-multilayer database. Our system uses, at the first stage, coarse screening by the proportional information on the hand images, which roughly correspond to forearm rotation or bending of the thumb or four fingers; then, at the second stage, performs a detailed search for similarity for selected candidates. To describe forearm rotation, and wrist’s internal and external rotations, bending and stretching, no separate processes were used for estimating the corresponding joint angles. By estimating the sequential images of the finger shape using this method, we successfully realized a process involving a joint angle estimation error within two or three degrees, a processing time of approximately 80 fps or more, using only one Note PC and high-speed camera, even when the wrist was freely rotating. Since the image information and the joint angle information are paired in the database, as well as the wrist joint, the system can generate the imitative motions as those of the fingers and wrist of a human being with no time delay by means of a robot, by outputting the estimation results to the robot hand.

This is a preview of subscription content, log in to check access.


  1. 1

    Rehg JM, Kanade T (1994) Visual tracking of high DOF articulated structures: an application to human hand tracking. In: European conference on computer vision, pp 35–46

  2. 2

    Kameda Y, Minoh M (1996) A human motion estimation method using 3-successive video frames. In: Proceedings of the virtual systems and multimedia, pp 135–140

  3. 3

    Lu S, Metaxas D, Samaras D, Oliensis J (2003) Using multiple cues for hand tracking and model refinement. In: Proceedings of the CVPR2003, vol 2, pp 443–450

  4. 4

    Gumpp T, Azad P, Welke K, Oztop E, Dillmann R, Cheng G (2006) Unconstrained real-time markerless hand tracking for humanoid interaction. In: Proceedings of the IEEE-RAS international conference on humanoid robots (Humanoids 2006), CD-ROM

  5. 5

    Athitos V, Scarloff S (2002) An appearance-based framework for 3D hand shape classification and camera viewpoint estimation. In: Proceedings of the automatic face and gesture recognition, pp 40–45

  6. 6

    Hoshino K, Tanimoto T (2005) Real time search for similar hand images from database for robotic hand control. In: IEICE transactions on fundamentals of electronics. Communications and computer sciences, E88-A, vol 10, pp 2514–2520

  7. 7

    Wu Y, Lin J, Huang TS (2005) Analyzing and capturing articulated hand motion in image sequences. IEEE Trans Pattern Anal Mach Intell 27(12): 1910–1922

  8. 8

    Hoshino K, Tamaki E, Tanimoto T (2007) Copycat hand—robot hand imitating human motions at high speed and with high accuracy. Adv Robotics 21(15): 1743–1761

  9. 9

    Tamaki E, Hoshino K (2007) 3D estimation of human hand posture with wrist motions, IEICE technical report. Welfare information technology vol 107, 179, pp 59–62 (in Japanese)

  10. 10

    Otsu N, Kurita T (1998) A new scheme for practical, flexible and intelligent vision systems. In: Proceedings of the IAPR workshop on computer vision, pp 431–435

  11. 11

    Hoshino K, Kawabuchi I (2005) Pinching at finger tips for humanoid robot hand. J Robotics Mechatronics 17(6): 655–663

  12. 12

    Hoshino K, Tanimoto T (2006) Realtime hand posture estimation with Self-Organizing Map for stable robot control. In: IEICE transactions on information and systems, E89-D, vol 6, pp 1813–1819

  13. 13

    Hoshino Lab.

Download references

Author information

Correspondence to Kiyoshi Hoshino.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Hoshino, K., Tomida, M. Quick and accurate estimation of human 3D hand posture. Intel Serv Robotics 3, 11 (2010).

Download citation


  • Hand posture estimation
  • 2D-appearance-based approach
  • 3D changes in the appearance of hands
  • Proportional information on the hand images
  • Imitative motions