10995

Digitize Your Body and Action in 3-D at Over 10 FPS: Real Time Dense Voxel Reconstruction and Marker-less Motion Tracking via GPU Acceleration

Jian Song, Yatao Bian, Junchi Yan, Xu Zhao, Yuncai Liu
Department of Automation, Shanghai Jiao Tong University, and Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China
arXiv:1311.6811 [cs.GR], (26 Nov 2013)

@article{2013arXiv1311.6811S,

   author={Song}, J. and {Bian}, Y. and {Yan}, J. and {Zhao}, X. and {Liu}, Y.},

   title={"{Digitize Your Body and Action in 3-D at Over 10 FPS: Real Time Dense Voxel Reconstruction and Marker-less Motion Tracking via GPU Acceleration}"},

   journal={ArXiv e-prints},

   archivePrefix={"arXiv"},

   eprint={1311.6811},

   primaryClass={"cs.GR"},

   keywords={Computer Science – Graphics},

   year={2013},

   month={nov},

   adsurl={http://adsabs.harvard.edu/abs/2013arXiv1311.6811S},

   adsnote={Provided by the SAO/NASA Astrophysics Data System}

}

Download Download (PDF)   View View   Source Source   

1761

views

In this paper, we present an approach to reconstruct 3-D human motion from multi-cameras and track human skeleton using the reconstructed human 3-D point (voxel) cloud. We use an improved and more robust algorithm, probabilistic shape from silhouette to reconstruct human voxel. In addition, the annealed particle filter is applied for tracking, where the measurement is computed using the reprojection of reconstructed voxel. We use two different ways to accelerate the approach. For the CPU only acceleration, we leverage Intel TBB to speed up the hot spot of the computational overhead and reached an accelerating ratio of 3.5 on a 4-core CPU. Moreover, we implement an intensively paralleled version via GPU acceleration without TBB. Taking account all data transfer and computing time, the GPU version is about 400 times faster than the original CPU implementation, leading the approach to run at a real-time speed.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: