Tracking in Action Space
The recognition of human actions such as pointing at objects (“Give me that...”) is difficult because they ought to be recognized independent of scene parameters such as viewing direction. Furthermore, the parameters of the action, such as pointing direction, are important pieces of information. One common way to achieve recognition is by using 3D human body tracking followed by action recognition based on the captured tracking data. General 3D body tracking is, however, still a difficult problem. In this paper, we are looking at human body tracking for action recognition from a context-driven perspective. Instead of the space of human body poses, we consider the space of possible actions of a given context and argue that 3D body tracking reduces to action tracking in the parameter space in which the actions live. This reduces the high-dimensional problem to a low-dimensional one. In our approach, we use parametric hidden Markov models to represent parametric movements; particle filtering is used to track in the space of action parameters. Our approach is content with monocular video data and we demonstrate its effectiveness on synthetic and on real image sequences. In the experiments we focus on human arm movements.
KeywordsAction Space Action Recognition Action Tracking Observation Function Action Primitive
Unable to display preview. Download preview PDF.
- 2.Krüger, V., Kragic, D., Ude, A., Geib, C.: The meaning of action: A review on action recognition and mapping. Advanced Robotics 21, 1473–1501 (2007)Google Scholar
- 4.Ren, H., Xu, G., Kee, S.: Subject-independent Natural Action Recognition. In: International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, May 17-19 (2004)Google Scholar
- 8.Deutscher, J., Blake, A., Reid, I.: Articulated body motion capture by annealed particle filtering. In: CVPR, vol. 2, pp. 126–133 (2000)Google Scholar
- 10.Sminchisescu, C., Triggs, B.: Covarinace Scaled Sampling for Monocular 3D Body Tracking. In: CVPR, Kauai Marriott, Hawaii (2001)Google Scholar
- 11.Gupta, A., Davis, L.: Objects in action: An approach for combining action understanding and object perception. In: CVPR (2007)Google Scholar
- 17.Guerra-Filho, G., Aloimonos, Y.: A sensory-motor language for human activity understanding. HUMANOIDS (2006)Google Scholar
- 18.Jenkins, O., Mataric, M.: Deriving Action and Behavior Primitives from Human Motion Data. In: International Conference on Intelligent Robots and Systems, Lausanne, Switzerland, September 30-October 4, pp. 2551–2556 (2002)Google Scholar
- 26.Elgammal, A., Lee, C.S.: Inferring 3D body pose from silhouettes using activity manifold learning. In: CVPR (2004)Google Scholar
- 28.Rabiner, L.R., Juang, B.H.: An introduction to hidden Markov models. IEEE ASSP Magazine, 4–15 (1986)Google Scholar