Motion capture system contextualization

ABSTRACT

The notion of contextualization has been introduced in an existing motion capture system driven by the segmented silhouettes of a person filmed from several points of view. The principle is to create a dependence of each module of the process (in this case, the different modules are the motion capture itself, the adaptive background modeling and the silhouette segmentation) from the results of the preceding ones. Thus, the influence of these elements, one with the other, guides locally the different computations. So, this optimization increases the reliability of the whole process while decreasing significantly its processing time. Yet it is obvious that this concept can be applied to several aspects of a motion capture system. As a matter of fact, it is possible to contextualize the captured motion, by modeling the context in which it takes place, allowing to make strong assumptions about the following sequence of movements executed by the filmed person. Thus, by recognizing the current and the next gestures of a captured person, the system can adapt its reactions and evolve with the constantly changing comprehension of the context by the player.

REFERENCES

• 1: Chalidabhongse, T. H., Kim, K., Harwood, D., Davis, L. A Perturbation Method for Evaluating Background Subtraction Algorithms. Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (VS-PETS 2003), Nice, France, Oct. 11--12, 2003
• 2: Collins, R. T., Lipton, A. J., Kanade, T., Fujiyoshi, H., Duggins, D., Tsin, Y., Tolliver, D., Enomoto, N., Hasegawa, O., Burt, P., Wixson, L. A System for Video Surveillance and Monitoring. VSAM Final Report, Technical report CMU-RITR-00-12, Robotics Institute, Carnegie Mellon University, May 2000.
• 3: Delamarre, Q. Suivi du mouvement d'objets articulés dans des séquences d'images vidéo. Doctoral Thesis, University of Nice-Sophia Antipolis, France, 2003.
• 4: KawTraKulPong, P., Bowden, R. An improved adaptive background mixture model for real-time tracking with shadow detection. Proceedings of Second European Workshop on Advanced Video-based Surveillance Systems, 2001.
• 5: Micheli, R. Contexte et contextualisation en analyse du discours: regard sur les travaux de T. Van Dijk. 2006, http://semen.revues.org/document1971.html.
• 6: Toyama, K., Krumm, J., Brumitt, B., Meyers, B. Wallflower: Principles and practice of background maintenance. Proceedings of IEEE International Conference on Computer Vision, p. 255--261, 1999.
• 7: Tao Yang , Stan Z. Li , Quan Pan , Jing Li, Real-time and accurate segmentation of moving objects in dynamic scene, Proceedings of the ACM 2nd international workshop on Video surveillance & sensor networks, October 15-15, 2004, New York, NY, USA [doi>10.1145/1026799.1026822]

INDEX TERMS

Primary Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.5 Reliability
          Subjects: Fault-tolerance

Additional Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.7 Organization and Design
          Subjects: Real-time systems and embedded systems
      D.4.8 Performance
          Subjects: Modeling and prediction

  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.6 Segmentation
          Subjects: Edge and feature detection
      I.4.8 Scene Analysis
          Subjects: Tracking; Motion

General Terms:
Algorithms, Management, Performance, Reliability

Keywords:
adaptive background modeling, contextualization, motion capture, motion prediction, silhouette segmentation