3D Markerless Motion Capture: A Low Cost Approach

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 444)

Abstract

A markerless motion capture technique is described for reconstructing three-dimensional biological motion. In the first stage of the process, an action is recorded with 2 CCD webcams. Then, the video is divided in frames. For each frame, the 2D coordinates of key locations (body joints) are extracted by the combination of manual identification (mouse pointing) and image processing (blobs matching). Finally, an algorithm computes the X-Y coordinates from each camera view to generate a file containing the 3D coordinates of every visible point in the display. This technique has many advantages over other methods. It does not require too specialized equipment. The computer programming uses open source software. The technology is based on an inexpensive portable device. Moreover, it can be used for different environments (indoor/outdoor) and living beings (human/animal). This system has already been tested in a wide range of applications, such as avatars modeling and psychophysical studies.

Keywords

Image processing 3D reconstruction Biological motion 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Heloir, A., Neff, M.: Exploiting Motion Capture for Virtual Human Animation: Data Collection and Annotation Visualization. In: Workshop on Multimodal Corpora - Advances in Capturing, Coding and Analyzing Multimodality. Valletta, Malta (2010)Google Scholar
  2. 2.
    Gameiro, J., Cardoso, T., Rybarczyk Y.: Kinect-Sign: Teaching Sign Language to Listeners through a Game. In: Rybarczyk, Y., Cardoso, T., Rosas, J., Camarinha-Matos, L. (eds.) Innovative and Creative Developments in Multimodal Interaction Systems, pp. 141–159. Springer, Heidelberg (2014)Google Scholar
  3. 3.
    Rybarczyk, Y., Santos, J.: Motion Integration in Direction Perception of Biological Motion. In: Fourth Asian Conference on Vision. Matsue, Japan (2006)Google Scholar
  4. 4.
    Dekeyser, M., Verfaillie, K., Vanrie, J.: Creating Stimuli for the Study of Biological Motion Perception. Behavior Research Methods, Instruments, & Computers 34(3), pp. 375–382 (2002)Google Scholar
  5. 5.
  6. 6.
    Vicon Motion Systems, http://www.vicon.com/
  7. 7.
    Shipley, T., Brumberg, J.: Markerless Motion Capture for Point-Light Displays. Technical report, available at http://astro.temple.edu/~tshipley/mocap.html
  8. 8.
    Zhang, Z., Troje, N. F.: 3D Periodic Human Motion Reconstruction from 2D Motion Sequences. Neural Computation 19, pp. 1400–1421 (2007)Google Scholar
  9. 9.
    Harmazi, M., Bensrhair, A., Bennouna, M., Miché, P., Mousset, S.: Implementation of a Real-Time 3D Vision Sensor for a Vehicle Driving Aid. In: TILT Conference. Lille, France (2003)Google Scholar
  10. 10.
    Shiffman, D.: Learning Processing: A Beginner’s Guide to Programming Images, Animation and Interaction. Morgan Kaufmann, San Francisco (2008).Google Scholar
  11. 11.
    Caillette, F., Aphrodite G., Toby H.: Real-Time 3-D Human Body Tracking Using Learnt Models of Behaviour. Computer Vision and Image Understanding 109(2), pp. 112–125 (2008)Google Scholar
  12. 12.
    Canton-Ferrer, C., Casas, J.R., Pardàs, M.: Human Motion Capture Using Scalable Body Models. Computer Vision and Image Understanding 115(10), pp. 1363–1374 (2011)Google Scholar
  13. 13.
    Dutta, T.: Evaluation of the Kinect Sensor for 3-D Kinematic Measurement in the Workplace. Applied Ergonomics 43, pp. 645–649 (2012)Google Scholar
  14. 14.
    Chen, L., Wei, H., Ferryman, J.: A Survey of Human Motion Analysis Using Depth Imagery. Pattern Recognition Letters 34, pp. 1995–2006 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.UNINOVA, DEE, FCTUniversidade NOVA de LisboaMonte de CaparicaPortugal
  2. 2.MISTUniversidad Tecnológica IndoaméricaQuitoEcuador

Personalised recommendations