Pixels2Pose: Super-Resolution Time-of-Flight Imaging for 3D Pose Estimation

Alice Ruget; Max Tyler; Germán Mora-Martín; Stirling Scholes; Feng Zhu; Istvan Gyongy; Brent Hearn; Steve McLaughlin; Abderrahim Halimi; Jonathan Leach

doi:10.1364/ISA.2022.ITh5D.5

Pixels2Pose: Super-Resolution Time-of-Flight Imaging for 3D Pose Estimation

Alice Ruget
, Max Tyler
, Germán Mora-Martín
, Stirling Scholes
, Feng Zhu
, Istvan Gyongy
, Brent Hearn
, Steve McLaughlin
, Abderrahim Halimi
, Jonathan Leach

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

156 Downloads (Pure)

Abstract

The process of tracking human anatomy in computer vision is called pose estimation. It traditionally requires advanced equipment. We develop a system that estimates the 3D poses of people from a cost-effective and compact time-of-flight sensor.

Original language	English
Title of host publication	Imaging Systems and Applications 2022
Publisher	Optica Publishing Group
ISBN (Electronic)	9781957171098
DOIs	https://doi.org/10.1364/ISA.2022.ITh5D.5
Publication status	Published - 2022
Event	Imaging Systems and Applications 2022 - Vancouver, Canada Duration: 11 Jul 2022 → 15 Jul 2022

Conference

Conference	Imaging Systems and Applications 2022
Abbreviated title	ISA 2022
Country/Territory	Canada
City	Vancouver
Period	11/07/22 → 15/07/22

Keywords

cs.CV

Access to Document

10.1364/ISA.2022.ITh5D.5

Download pdf

Cite this

@inproceedings{458343d0e6154e71b61434fcb3707f9d,

title = "Pixels2Pose: Super-Resolution Time-of-Flight Imaging for 3D Pose Estimation",

abstract = "The process of tracking human anatomy in computer vision is called pose estimation. It traditionally requires advanced equipment. We develop a system that estimates the 3D poses of people from a cost-effective and compact time-of-flight sensor.",

keywords = "cs.CV",

author = "Alice Ruget and Max Tyler and Germ{\'a}n Mora-Mart{\'i}n and Stirling Scholes and Feng Zhu and Istvan Gyongy and Brent Hearn and Steve McLaughlin and Abderrahim Halimi and Jonathan Leach",

note = "Funding Information: This work was supported by EPSRC through grants EP/S001638/1, EP/T00097X/1 and EP/S026428/1. Also it is supported by the UK Royal Academy of Engineering Research Fellowship Scheme (Project RF/201718/17128) and DSTL Dasa project DSTLX1000147844. We thank the authors of OpenPose [1] for their code. Code for generating the 3D pose from the ToF sensor can be found at https://github.com/HWQuantum/Real-time-low-cost-multi-person-3D-pose-estimation. The trained networks are available at https://researchportal.hw.ac.uk/en/datasets/real-time-low-cost-multi-person-3d-pose-estimation. Publisher Copyright: {\textcopyright} 2022 The Author(s); Imaging Systems and Applications 2022, ISA 2022 ; Conference date: 11-07-2022 Through 15-07-2022",

year = "2022",

doi = "10.1364/ISA.2022.ITh5D.5",

language = "English",

booktitle = "Imaging Systems and Applications 2022",

publisher = "Optica Publishing Group",

address = "United States",

}

Ruget, A, Tyler, M, Mora-Martín, G, Scholes, S, Zhu, F, Gyongy, I, Hearn, B, McLaughlin, S , Halimi, A & Leach, J 2022, Pixels2Pose: Super-Resolution Time-of-Flight Imaging for 3D Pose Estimation. in Imaging Systems and Applications 2022., ITh5D.5, Optica Publishing Group, Imaging Systems and Applications 2022, Vancouver, Canada, 11/07/22. https://doi.org/10.1364/ISA.2022.ITh5D.5

TY - GEN

T1 - Pixels2Pose

T2 - Imaging Systems and Applications 2022

AU - Ruget, Alice

AU - Tyler, Max

AU - Mora-Martín, Germán

AU - Scholes, Stirling

AU - Zhu, Feng

AU - Gyongy, Istvan

AU - Hearn, Brent

AU - McLaughlin, Steve

AU - Halimi, Abderrahim

AU - Leach, Jonathan

N1 - Funding Information: This work was supported by EPSRC through grants EP/S001638/1, EP/T00097X/1 and EP/S026428/1. Also it is supported by the UK Royal Academy of Engineering Research Fellowship Scheme (Project RF/201718/17128) and DSTL Dasa project DSTLX1000147844. We thank the authors of OpenPose [1] for their code. Code for generating the 3D pose from the ToF sensor can be found at https://github.com/HWQuantum/Real-time-low-cost-multi-person-3D-pose-estimation. The trained networks are available at https://researchportal.hw.ac.uk/en/datasets/real-time-low-cost-multi-person-3d-pose-estimation. Publisher Copyright: © 2022 The Author(s)

PY - 2022

Y1 - 2022

N2 - The process of tracking human anatomy in computer vision is called pose estimation. It traditionally requires advanced equipment. We develop a system that estimates the 3D poses of people from a cost-effective and compact time-of-flight sensor.

AB - The process of tracking human anatomy in computer vision is called pose estimation. It traditionally requires advanced equipment. We develop a system that estimates the 3D poses of people from a cost-effective and compact time-of-flight sensor.

KW - cs.CV

UR - https://www.scopus.com/pages/publications/85139552289

U2 - 10.1364/ISA.2022.ITh5D.5

DO - 10.1364/ISA.2022.ITh5D.5

M3 - Conference contribution

BT - Imaging Systems and Applications 2022

PB - Optica Publishing Group

Y2 - 11 July 2022 through 15 July 2022

ER -

Pixels2Pose: Super-Resolution Time-of-Flight Imaging for 3D Pose Estimation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this