High-Speed Multi-Person Pose Estimation with Deep Feature Transfer

High-Speed Multi-Person Pose Estimation with Deep Feature Transfer

Abstract

Recent advancements in deep learning have significantly improved the accuracy of multi-person pose estimation from RGB images. However, these deep learning methods typically rely on a large number of deep refinement modules to refine the features of body joints and limbs, which hugely reduce the run-time speed and therefore limit the application domain. In this paper, we propose a feature transfer framework to capture the concurrent correlations between body joint and limb features. The concurrent correlations of these features form a complementary structural relationship, which mutually strengthens the network’s inferences and reduces the needs of refinement modules. The transfer sub-network is implemented with multiple convolutional layers, and is merged with the body part detection network to form an end-to-end system. The transfer relationship is automatically learned from ground-truth data instead of being manually encoded, resulting in a more general and efficient design. The proposed framework is validated on the multiple popular multi-person pose estimation benchmarks - MPII, COCO 2018 and PoseTrack 2017 and 2018. Experimental results show that our method not only significantly increases the inference speed to 73.8 frame per second (FPS), but also attains comparable state-of-the-art performance.

Publication

Ying Huang, Hubert P. H. Shum, Edmond S. L. Ho and Nauman Aslam,
"High-Speed Multi-Person Pose Estimation with Deep Feature Transfer",
Computer Vision and Image Understanding (CVIU)

IF=3.121#

# Impact factors from the Journal Citation Reports 2019

Downloads

YouTube

References

BibTeX

@article{huang20highspeed,
 author={Huang, Ying and Shum, Hubert P. H. and Ho, Edmond S. L. and Aslam, Nauman},
 journal={Computer Vision and Image Understanding},
 title={High-Speed Multi-Person Pose Estimation with Deep Feature Transfer},
 year={2020},
 numpages={14},
 doi={10.1016/j.cviu.2020.103010},
 issn={1077-3142},
 publisher={Elsevier},
}

EndNote/RefMan

TY  - JOUR
AU  - Huang, Ying
AU  - Shum, Hubert P. H.
AU  - Ho, Edmond S. L.
AU  - Aslam, Nauman
T2  - Computer Vision and Image Understanding
TI  - High-Speed Multi-Person Pose Estimation with Deep Feature Transfer
PY  - 2020
DO  - 10.1016/j.cviu.2020.103010
SN  - 1077-3142
PB  - Elsevier
ER  - 

Plain Text

Ying Huang, Hubert P. H. Shum, Edmond S. L. Ho and Nauman Aslam, "High-Speed Multi-Person Pose Estimation with Deep Feature Transfer," Computer Vision and Image Understanding, Elsevier, 2020.

Similar Research

 

         

Last update: 10/08/2020