3D Human Pose Estimation Using WiFi Signals

Yili Ren; Zi Wang; Yichao Wang; Sheng Tan; Yingying Chen; Jie Yang

doi:10.1145/3485730.3492871

3D Human Pose Estimation Using WiFi Signals

Yili Ren, Zi Wang, Yichao Wang, Sheng Tan, Yingying Chen, Jie Yang

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

5 Scopus citations

Abstract

This paper presents GoPose, a 3D skeleton-based human pose estimation system that uses commodity WiFi devices at home. Our system leverages the WiFi signals reflected off the human body for 3D pose estimation. In contrast to prior systems that need dedicated sensors, our system does not require a user to wear any sensors and can reuse the WiFi devices that already exist in a home environment for mass adoption. To realize such a system, we leverage the 2D AoA estimation of the signals reflected from the human body and the deep learning techniques. Preliminary results show GoPose achieves a high accuracy of 4.5cm in various scenarios.

Original language	English (US)
Title of host publication	SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems
Publisher	Association for Computing Machinery, Inc
Pages	363-364
Number of pages	2
ISBN (Electronic)	9781450390972
DOIs	https://doi.org/10.1145/3485730.3492871
State	Published - Nov 15 2021
Externally published	Yes
Event	19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021 - Coimbra, Portugal Duration: Nov 15 2021 → Nov 17 2021

Publication series

Name	SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems

Conference

Conference	19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021
Country/Territory	Portugal
City	Coimbra
Period	11/15/21 → 11/17/21

Keywords

Channel State Information (CSI)
Deep Learning
Human Pose Estimation
WiFi Sensing

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1145/3485730.3492871

Cite this

Ren, Y., Wang, Z., Wang, Y., Tan, S., Chen, Y., & Yang, J. (2021). 3D Human Pose Estimation Using WiFi Signals. In SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems (pp. 363-364). (SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems). Association for Computing Machinery, Inc. https://doi.org/10.1145/3485730.3492871

3D Human Pose Estimation Using WiFi Signals. / Ren, Yili; Wang, Zi; Wang, Yichao et al.
SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems. Association for Computing Machinery, Inc, 2021. p. 363-364 (SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems).

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

Ren, Y, Wang, Z, Wang, Y, Tan, S, Chen, Y & Yang, J 2021, 3D Human Pose Estimation Using WiFi Signals. in SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems. SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems, Association for Computing Machinery, Inc, pp. 363-364, 19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021, Coimbra, Portugal, 11/15/21. https://doi.org/10.1145/3485730.3492871

Ren Y, Wang Z, Wang Y, Tan S, Chen Y, Yang J. 3D Human Pose Estimation Using WiFi Signals. In SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems. Association for Computing Machinery, Inc. 2021. p. 363-364. (SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems). doi: 10.1145/3485730.3492871

@inproceedings{1b8d63914f3346509dcff0c16fa0f1e1,

title = "3D Human Pose Estimation Using WiFi Signals",

abstract = "This paper presents GoPose, a 3D skeleton-based human pose estimation system that uses commodity WiFi devices at home. Our system leverages the WiFi signals reflected off the human body for 3D pose estimation. In contrast to prior systems that need dedicated sensors, our system does not require a user to wear any sensors and can reuse the WiFi devices that already exist in a home environment for mass adoption. To realize such a system, we leverage the 2D AoA estimation of the signals reflected from the human body and the deep learning techniques. Preliminary results show GoPose achieves a high accuracy of 4.5cm in various scenarios.",

keywords = "Channel State Information (CSI), Deep Learning, Human Pose Estimation, WiFi Sensing",

author = "Yili Ren and Zi Wang and Yichao Wang and Sheng Tan and Yingying Chen and Jie Yang",

note = "Publisher Copyright: {\textcopyright} 2021 Owner/Author.; 19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021 ; Conference date: 15-11-2021 Through 17-11-2021",

year = "2021",

month = nov,

day = "15",

doi = "10.1145/3485730.3492871",

language = "English (US)",

series = "SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems",

publisher = "Association for Computing Machinery, Inc",

pages = "363--364",

booktitle = "SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems",

}

TY - GEN

T1 - 3D Human Pose Estimation Using WiFi Signals

AU - Ren, Yili

AU - Wang, Zi

AU - Wang, Yichao

AU - Tan, Sheng

AU - Chen, Yingying

AU - Yang, Jie

PY - 2021/11/15

Y1 - 2021/11/15

N2 - This paper presents GoPose, a 3D skeleton-based human pose estimation system that uses commodity WiFi devices at home. Our system leverages the WiFi signals reflected off the human body for 3D pose estimation. In contrast to prior systems that need dedicated sensors, our system does not require a user to wear any sensors and can reuse the WiFi devices that already exist in a home environment for mass adoption. To realize such a system, we leverage the 2D AoA estimation of the signals reflected from the human body and the deep learning techniques. Preliminary results show GoPose achieves a high accuracy of 4.5cm in various scenarios.

AB - This paper presents GoPose, a 3D skeleton-based human pose estimation system that uses commodity WiFi devices at home. Our system leverages the WiFi signals reflected off the human body for 3D pose estimation. In contrast to prior systems that need dedicated sensors, our system does not require a user to wear any sensors and can reuse the WiFi devices that already exist in a home environment for mass adoption. To realize such a system, we leverage the 2D AoA estimation of the signals reflected from the human body and the deep learning techniques. Preliminary results show GoPose achieves a high accuracy of 4.5cm in various scenarios.

KW - Channel State Information (CSI)

KW - Deep Learning

KW - Human Pose Estimation

KW - WiFi Sensing

UR - http://www.scopus.com/inward/record.url?scp=85119824357&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85119824357&partnerID=8YFLogxK

U2 - 10.1145/3485730.3492871

DO - 10.1145/3485730.3492871

M3 - Conference contribution

AN - SCOPUS:85119824357

T3 - SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems

SP - 363

EP - 364

BT - SenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems

PB - Association for Computing Machinery, Inc

T2 - 19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021

Y2 - 15 November 2021 through 17 November 2021

ER -

3D Human Pose Estimation Using WiFi Signals

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this