Real-Time Multi-scale Action Detection from 3D Skeleton Data

@article{Sharaf2015RealTimeMA,
  title={Real-Time Multi-scale Action Detection from 3D Skeleton Data},
  author={Amr Sharaf and Marwan Torki and Mohamed E. Hussein and Motaz El-Saban},
  journal={2015 IEEE Winter Conference on Applications of Computer Vision},
  year={2015},
  pages={998-1005}
}
In this paper we introduce a real-time system for action detection. The system uses a small set of robust features extracted from 3D skeleton data. Features are effectively described based on the probability distribution of skeleton data. The descriptor computes a pyramid of sample covariance matrices and mean vectors to encode the relationship between the features. For handling the intra-class variations of actions, such as action temporal scale variations, the descriptor is computed using… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 26 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 28 references

Similar Papers

Loading similar papers…