A recognition-based motion capture baseline on the HumanEva II test data

@article{Howe2011ARM,
  title={A recognition-based motion capture baseline on the HumanEva II test data},
  author={Nicholas R. Howe},
  journal={Machine Vision and Applications},
  year={2011},
  volume={22},
  pages={995-1008}
}
The advent of the HumanEva standardized motion capture data sets has enabled quantitative evaluation of motion capture algorithms on comparable terms. This paper measures the performance of an existing monocular recognition-based pose recovery algorithm on select HumanEva data, including all the HumanEva II clips. The method uses a physically motivated Markov process to connect adjacent frames and achieve a 3D relative mean error of 8.9 cm per joint. It further investigates factors contributing… CONTINUE READING
9 Citations
44 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-9 of 9 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 44 references

A spatiotemporal 2D-models framework for human pose recovery in monocular sequences

  • G. Rogez, C. Orrite-Uruñuelaa, J. Martínez-del Rincón
  • Pattern Recognit. 41(9), 2926–2944
  • 2008
2 Excerpts

Similar Papers

Loading similar papers…