End-to-end feature pyramid network for real-time multi-person pose estimation

Dingli Luo; Songlin Du; Takeshi Ikenaga

doi:10.23919/MVA.2019.8758029

End-to-end feature pyramid network for real-time multi-person pose estimation

Dingli Luo, Songlin Du, Takeshi Ikenaga

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

In computer vision, pose estimation system is widely used to construct human body transformation. However, it is hard to achieve these targets together: Stable real-time speed, variance human number and high accuracy. This paper proposes an end-to-end pose estimation network. It contains a neural network friendly representation of human pose. Then it proposes a correspond real-time end-to-end pose estimation network based on feature pyramid network structure with attention-based detection modules. This network can detect multiple humans in more than 60 fps with 384 x 384 resolution on GTX 1070 with affordable accuracy. This work shows the potential of this network structure can perform both faster and better compared with state-of-the-art results.

Original language	English
Title of host publication	Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9784901122184
DOIs	https://doi.org/10.23919/MVA.2019.8758029
Publication status	Published - 2019 May
Externally published	Yes
Event	16th International Conference on Machine Vision Applications, MVA 2019 - Tokyo, Japan Duration: 2019 May 27 → 2019 May 31

Publication series

Name	Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

Conference

Conference	16th International Conference on Machine Vision Applications, MVA 2019
Country/Territory	Japan
City	Tokyo
Period	19/5/27 → 19/5/31

ASJC Scopus subject areas

Computer Science Applications
Signal Processing
Computer Vision and Pattern Recognition

Access to Document

10.23919/MVA.2019.8758029

Cite this

Luo, D., Du, S., & Ikenaga, T. (2019). End-to-end feature pyramid network for real-time multi-person pose estimation. In Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019 Article 8758029 (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/MVA.2019.8758029

End-to-end feature pyramid network for real-time multi-person pose estimation. / Luo, Dingli; Du, Songlin; Ikenaga, Takeshi.
Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8758029 (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Luo, D, Du, S & Ikenaga, T 2019, End-to-end feature pyramid network for real-time multi-person pose estimation. in Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019., 8758029, Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019, Institute of Electrical and Electronics Engineers Inc., 16th International Conference on Machine Vision Applications, MVA 2019, Tokyo, Japan, 19/5/27. https://doi.org/10.23919/MVA.2019.8758029

Luo D, Du S, Ikenaga T. End-to-end feature pyramid network for real-time multi-person pose estimation. In Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8758029. (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019). doi: 10.23919/MVA.2019.8758029

Luo, Dingli ; Du, Songlin ; Ikenaga, Takeshi. / End-to-end feature pyramid network for real-time multi-person pose estimation. Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019).

@inproceedings{f84fd865ddd0423680e0b2e5fdadffe4,

title = "End-to-end feature pyramid network for real-time multi-person pose estimation",

abstract = "In computer vision, pose estimation system is widely used to construct human body transformation. However, it is hard to achieve these targets together: Stable real-time speed, variance human number and high accuracy. This paper proposes an end-to-end pose estimation network. It contains a neural network friendly representation of human pose. Then it proposes a correspond real-time end-to-end pose estimation network based on feature pyramid network structure with attention-based detection modules. This network can detect multiple humans in more than 60 fps with 384 x 384 resolution on GTX 1070 with affordable accuracy. This work shows the potential of this network structure can perform both faster and better compared with state-of-the-art results.",

author = "Dingli Luo and Songlin Du and Takeshi Ikenaga",

note = "Publisher Copyright: {\textcopyright} 2019 MVA Organization.; 16th International Conference on Machine Vision Applications, MVA 2019 ; Conference date: 27-05-2019 Through 31-05-2019",

year = "2019",

month = may,

doi = "10.23919/MVA.2019.8758029",

language = "English",

series = "Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019",

}

TY - GEN

T1 - End-to-end feature pyramid network for real-time multi-person pose estimation

AU - Luo, Dingli

AU - Du, Songlin

AU - Ikenaga, Takeshi

PY - 2019/5

Y1 - 2019/5

N2 - In computer vision, pose estimation system is widely used to construct human body transformation. However, it is hard to achieve these targets together: Stable real-time speed, variance human number and high accuracy. This paper proposes an end-to-end pose estimation network. It contains a neural network friendly representation of human pose. Then it proposes a correspond real-time end-to-end pose estimation network based on feature pyramid network structure with attention-based detection modules. This network can detect multiple humans in more than 60 fps with 384 x 384 resolution on GTX 1070 with affordable accuracy. This work shows the potential of this network structure can perform both faster and better compared with state-of-the-art results.

AB - In computer vision, pose estimation system is widely used to construct human body transformation. However, it is hard to achieve these targets together: Stable real-time speed, variance human number and high accuracy. This paper proposes an end-to-end pose estimation network. It contains a neural network friendly representation of human pose. Then it proposes a correspond real-time end-to-end pose estimation network based on feature pyramid network structure with attention-based detection modules. This network can detect multiple humans in more than 60 fps with 384 x 384 resolution on GTX 1070 with affordable accuracy. This work shows the potential of this network structure can perform both faster and better compared with state-of-the-art results.

UR - http://www.scopus.com/inward/record.url?scp=85070482908&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070482908&partnerID=8YFLogxK

U2 - 10.23919/MVA.2019.8758029

DO - 10.23919/MVA.2019.8758029

M3 - Conference contribution

AN - SCOPUS:85070482908

T3 - Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

BT - Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th International Conference on Machine Vision Applications, MVA 2019

Y2 - 27 May 2019 through 31 May 2019

ER -

End-to-end feature pyramid network for real-time multi-person pose estimation

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this