DHP19: Dynamic Vision Sensor 3D Human Pose Dataset

@inproceedings{Calabrese2019DHP19DV,
  title={DHP19: Dynamic Vision Sensor 3D Human Pose Dataset},
  author={Enrico Calabrese and Gemma Taverni and Christopher Awai Easthope and Sophie Skriabine and Federico Corradi and Luca Longinotti and Kynan Eng and Tobi Delbruck},
  booktitle={CVPR 2019},
  year={2019}
}
  • Enrico Calabrese, Gemma Taverni, +5 authors Tobi Delbruck
  • Published in CVPR 2019
Human pose estimation has dramatically improved thanks to the continuous developments in deep learning. However, marker-free human pose estimation based on standard frame-based cameras is still slow and power hungry for real-time feedback interaction because of the huge number of operations necessary for large Convolutional Neural Network (CNN) inference. Event-based cameras such as the Dynamic Vision Sensor (DVS) quickly output sparse moving-edge information. Their sparse and rapid output is… CONTINUE READING

Citations

Publications citing this paper.

EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera

Lan Xu, Weipeng Xu, +3 authors Christian Theobalt
  • ArXiv
  • 2019
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

A low power, fully event-based gesture recognition system

Arnon Amir
  • In IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
  • 2017
VIEW 2 EXCERPTS

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 2 EXCERPTS

Single-Shot Multi-person 3D Pose Estimation from Monocular RGB

  • 2018 International Conference on 3D Vision (3DV)
  • 2017
VIEW 1 EXCERPT