Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation

Ziheng Chi; Shaozhi Wang; Xinyue Li; Chun Tzu Chang; Md Islam; Akshay Holkar; Samantha Pronger; Tianshan Liu; Kin Man Lam; Xiangjian He

doi:10.1117/12.2626114

Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation

Ziheng Chi, Shaozhi Wang, Xinyue Li, Chun Tzu Chang, Md Islam, Akshay Holkar, Samantha Pronger, Tianshan Liu, Kin Man Lam, Xiangjian He

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

In-bed pose estimation is of great value in current health-monitoring systems. In this paper, we solve a cross-domain pose estimation problem, in which a fully annotated uncovered training set is used for pose estimation learning, and a large-scale unlabelled data set of covered images is employed for unsupervised domain adaptation. To tackle this challenging problem, we propose a multi-level domain adaptation framework, which learns a generalizable pose estimation network based three levels of adaptation. We evaluate the proposed framework on a public in-bed pose estimation benchmark. The results demonstrate that our proposed framework can effectively generalize the learned knowledge from the uncovered source domain to the covered target domain for privacy-protected in-bed pose estimation.

Original language	English
Title of host publication	International Workshop on Advanced Imaging Technology, IWAIT 2022
Editors	Masayuki Nakajima, Shogo Muramatsu, Jae-Gon Kim, Jing-Ming Guo, Qian Kemao
Publisher	SPIE
Volume	12177
ISBN (Electronic)	9781510653313
ISBN (Print)	9781510653313
DOIs	https://doi.org/10.1117/12.2626114
Publication status	Published - 2022
Externally published	Yes
Event	2022 International Workshop on Advanced Imaging Technology, IWAIT 2022 - Hong Kong, China Duration: 4 Jan 2022 → 6 Jan 2022

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	12177
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	2022 International Workshop on Advanced Imaging Technology, IWAIT 2022
Country/Territory	China
City	Hong Kong
Period	4/01/22 → 6/01/22

Keywords

In-bed human pose estimation
Privacy protection
Unsupervised domain adaption

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1117/12.2626114

Cite this

Chi, Z., Wang, S., Li, X., Chang, C. T., Islam, M., Holkar, A., Pronger, S., Liu, T., Lam, K. M., & He, X. (2022). Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation. In M. Nakajima, S. Muramatsu, J.-G. Kim, J.-M. Guo, & Q. Kemao (Eds.), International Workshop on Advanced Imaging Technology, IWAIT 2022 (Vol. 12177). Article 1217726 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12177). SPIE. https://doi.org/10.1117/12.2626114

Chi, Ziheng ; Wang, Shaozhi ; Li, Xinyue et al. / Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation. International Workshop on Advanced Imaging Technology, IWAIT 2022. editor / Masayuki Nakajima ; Shogo Muramatsu ; Jae-Gon Kim ; Jing-Ming Guo ; Qian Kemao. Vol. 12177 SPIE, 2022. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{26817dc05a914384a3874cd293631fcf,

title = "Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation",

abstract = "In-bed pose estimation is of great value in current health-monitoring systems. In this paper, we solve a cross-domain pose estimation problem, in which a fully annotated uncovered training set is used for pose estimation learning, and a large-scale unlabelled data set of covered images is employed for unsupervised domain adaptation. To tackle this challenging problem, we propose a multi-level domain adaptation framework, which learns a generalizable pose estimation network based three levels of adaptation. We evaluate the proposed framework on a public in-bed pose estimation benchmark. The results demonstrate that our proposed framework can effectively generalize the learned knowledge from the uncovered source domain to the covered target domain for privacy-protected in-bed pose estimation.",

keywords = "In-bed human pose estimation, Privacy protection, Unsupervised domain adaption",

author = "Ziheng Chi and Shaozhi Wang and Xinyue Li and Chang, {Chun Tzu} and Md Islam and Akshay Holkar and Samantha Pronger and Tianshan Liu and Lam, {Kin Man} and Xiangjian He",

note = "Publisher Copyright: {\textcopyright} 2022 SPIE.; 2022 International Workshop on Advanced Imaging Technology, IWAIT 2022 ; Conference date: 04-01-2022 Through 06-01-2022",

year = "2022",

doi = "10.1117/12.2626114",

language = "English",

isbn = "9781510653313",

volume = "12177",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Masayuki Nakajima and Shogo Muramatsu and Jae-Gon Kim and Jing-Ming Guo and Qian Kemao",

booktitle = "International Workshop on Advanced Imaging Technology, IWAIT 2022",

address = "United States",

}

Chi, Z, Wang, S, Li, X, Chang, CT, Islam, M, Holkar, A, Pronger, S, Liu, T, Lam, KM & He, X 2022, Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation. in M Nakajima, S Muramatsu, J-G Kim, J-M Guo & Q Kemao (eds), International Workshop on Advanced Imaging Technology, IWAIT 2022. vol. 12177, 1217726, Proceedings of SPIE - The International Society for Optical Engineering, vol. 12177, SPIE, 2022 International Workshop on Advanced Imaging Technology, IWAIT 2022, Hong Kong, China, 4/01/22. https://doi.org/10.1117/12.2626114

Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation. / Chi, Ziheng; Wang, Shaozhi; Li, Xinyue et al.
International Workshop on Advanced Imaging Technology, IWAIT 2022. ed. / Masayuki Nakajima; Shogo Muramatsu; Jae-Gon Kim; Jing-Ming Guo; Qian Kemao. Vol. 12177 SPIE, 2022. 1217726 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 12177).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation

AU - Chi, Ziheng

AU - Wang, Shaozhi

AU - Li, Xinyue

AU - Chang, Chun Tzu

AU - Islam, Md

AU - Holkar, Akshay

AU - Pronger, Samantha

AU - Liu, Tianshan

AU - Lam, Kin Man

AU - He, Xiangjian

PY - 2022

Y1 - 2022

N2 - In-bed pose estimation is of great value in current health-monitoring systems. In this paper, we solve a cross-domain pose estimation problem, in which a fully annotated uncovered training set is used for pose estimation learning, and a large-scale unlabelled data set of covered images is employed for unsupervised domain adaptation. To tackle this challenging problem, we propose a multi-level domain adaptation framework, which learns a generalizable pose estimation network based three levels of adaptation. We evaluate the proposed framework on a public in-bed pose estimation benchmark. The results demonstrate that our proposed framework can effectively generalize the learned knowledge from the uncovered source domain to the covered target domain for privacy-protected in-bed pose estimation.

AB - In-bed pose estimation is of great value in current health-monitoring systems. In this paper, we solve a cross-domain pose estimation problem, in which a fully annotated uncovered training set is used for pose estimation learning, and a large-scale unlabelled data set of covered images is employed for unsupervised domain adaptation. To tackle this challenging problem, we propose a multi-level domain adaptation framework, which learns a generalizable pose estimation network based three levels of adaptation. We evaluate the proposed framework on a public in-bed pose estimation benchmark. The results demonstrate that our proposed framework can effectively generalize the learned knowledge from the uncovered source domain to the covered target domain for privacy-protected in-bed pose estimation.

KW - In-bed human pose estimation

KW - Privacy protection

KW - Unsupervised domain adaption

UR - http://www.scopus.com/inward/record.url?scp=85131792335&partnerID=8YFLogxK

U2 - 10.1117/12.2626114

DO - 10.1117/12.2626114

M3 - Conference contribution

AN - SCOPUS:85131792335

SN - 9781510653313

VL - 12177

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Workshop on Advanced Imaging Technology, IWAIT 2022

A2 - Nakajima, Masayuki

A2 - Muramatsu, Shogo

A2 - Kim, Jae-Gon

A2 - Guo, Jing-Ming

A2 - Kemao, Qian

PB - SPIE

T2 - 2022 International Workshop on Advanced Imaging Technology, IWAIT 2022

Y2 - 4 January 2022 through 6 January 2022

ER -

Chi Z, Wang S, Li X, Chang CT, Islam M, Holkar A et al. Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation. In Nakajima M, Muramatsu S, Kim JG, Guo JM, Kemao Q, editors, International Workshop on Advanced Imaging Technology, IWAIT 2022. Vol. 12177. SPIE. 2022. 1217726. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2626114

Multi-Level Unsupervised Domain Adaption for Privacy-protected In-bed Pose Estimation

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this