Advertisement

Multimedia Tools and Applications

, Volume 75, Issue 16, pp 9669–9684 | Cite as

Feature design scheme for Kinect-based DTW human gesture recognition

  • Ing-Jr DingEmail author
  • Che-Wei Chang
Article

Abstract

Feature selection is a crucial factor in Kinect-based pattern recognition, including common human gesture recognition. For Kinect-based human gesture recognition, the information contained in the feature extracted for gesture recognition is conventionally the (x,y,z) coordinates of the primary joints in the human body. However, such traditionally used feature information containing only joint positions is apparently insufficient for clearly describing the characteristics of human activity patterns. This paper proposes a feature design scheme involving hybridizations of joint positions and joint angles for human gesture recognition with the Kinect camera. The presented feature design method effectively hybridizes the 20 main human joint positions captured by the Kinect camera and the joint angle information of 12 critical joints, along with significant angle variations when a gesture is made. The method is employed in dynamic time warping (DTW) gesture recognition. When the proposed feature design method is used for Kinect-based DTW human gesture recognition, it derives an appropriately sized feature vector for each of the gesture categories in the DTW-referenced template database according to the activity characteristics of a certain category of gestures. Experiments on Kinect-based DTW gesture recognition involving 14 common categories of human gestures show that the feature determined using the proposed approach is superior to that obtained using the conventional approach, which considers only the joint position information.

Keywords

Kinect camera Human gesture recognition Gesture feature DTW Recognition performance 

Notes

Acknowledgments

This research is partially supported by the Ministry of Science and Technology (MOST) in Taiwan under Grant MOST 103-2221-E-150-046.

References

  1. 1.
    Bautista MÁ, Hernández-Vela A, Ponce V, Perez-Sala X, Baró X, Pujol O, Angulo C, Escalera S (2013) Probability-based dynamic time warping for gesture recognition on RGB-D data. Lect Notes Comput Sci 7854:126–135CrossRefGoogle Scholar
  2. 2.
    Carmona JM, Climent J (2012) A performance evaluation of HMM and DTW for gesture recognition. Lect Notes Comput Sci 7441:236–243CrossRefGoogle Scholar
  3. 3.
    Ding IJ (2013) Speech recognition using variable-length frame overlaps by intelligent fuzzy control. J Intell Fuzzy Syst 25(1):49–56Google Scholar
  4. 4.
    Ding IJ, Chang CW An eigenspace-based method with a user adaptation scheme for human gesture recognition by using Kinect 3D data. Appl Math Model. doi: 10.1016/j.apm.2014.12.054
  5. 5.
    Ding IJ, Chang CW An adaptive hidden Markov model-based gesture recognition approach using Kinect to simplify large-scale video data processing for humanoid robot imitation. Multimed Tools Appl. doi: 10.1007/s11042-015-2505-9
  6. 6.
    Ding IJ, Yen CT (2013) Enhancing GMM speaker identification by incorporating SVM speaker verification for intelligent web-based speech applications. Multimed Tools Appl. doi: 10.1007/s11042-013-1587-5 Google Scholar
  7. 7.
    Han J, Shao L, Xu D, Shotton J (2013) Enhanced computer vision with microsoft Kinect sensor: a review. IEEE Trans Cybern 43(5):2168–2267Google Scholar
  8. 8.
    Nguyen-Duc-Thanh N, Lee S, Kim D (2012) Two-stage hidden Markov model in gesture recognition for human robot interaction. Int J Adv Robot Syst 9:1–10CrossRefGoogle Scholar
  9. 9.
    Qian K, Niu J, Yang H (2013) Developing a gesture based remote human-robot interaction system using Kinect. Int J Smart Home 7(4):203–208Google Scholar
  10. 10.
    Sakoe H, Chiba S (1978) Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans Acoust Speech Signal Process 26(1):43–49CrossRefzbMATHGoogle Scholar
  11. 11.
    Su CJ (2013) Personal rehabilitation exercise assistant with Kinect and dynamic time warping. Int J Inform Educ Technol 3(4):448–454CrossRefGoogle Scholar
  12. 12.
    Su CJ, Huang JY, Huang SF (2012) Ensuring home-based rehabilitation exercise by using Kinect and fuzzified dynamic time warping algorithm. Proc. the Asia Pacific Industrial Engineering & Management Systems Conference, pp. 884–895Google Scholar
  13. 13.
    Tashev I (2013) Kinect development kit: a toolkit for gesture- and speech based human-machine interaction. IEEE Signal Process Mag 30(5):129–131CrossRefGoogle Scholar
  14. 14.
    Wu J, Konrad J, Ishwar P (2013) Dynamic time warping for gesture-based user identification and authentication with Kinect. Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2371–2375Google Scholar
  15. 15.
    Xu W, Lee EJ (2012) Continuous gesture recognition system using improved HMM algorithm based on 2D and 3D space. Int J Multimed Ubiquitous Eng 7(2):335–340MathSciNetGoogle Scholar
  16. 16.
    Zhang L, Hsieh JC, Wang J (2012) A Kinect-based golf swing classification system using HMM and neuro-fuzzy. Proc. IEEE International Conference on Computer Science and Information Processing (CSIP), pp. 1163–1166Google Scholar
  17. 17.
    Zhang X, Ye Z, Jin L, Feng Z, Xu S (2013) A new writing experience: finger writing in the air using a Kinect sensor. IEEE MultiMed 20(4):85–93CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Department of Electrical EngineeringNational Formosa UniversityYunlin CountyTaiwan

Personalised recommendations