The University of Southampton
University of Southampton Institutional Repository

Real-time omnidirectional 3D multi-person human pose estimation with occlusion handling

Real-time omnidirectional 3D multi-person human pose estimation with occlusion handling
Real-time omnidirectional 3D multi-person human pose estimation with occlusion handling
We present a multi-person 3D human pose estimation system that addresses a major limitation in existing models, namely the focus on single person pose estimation. By using an off-the-shelf 2D detectors and 2D-3D lifting model, we first obtain the 3D poses of detected individuals in theirown local coordinate system from video. We then use a radar sensing data and people-matching approach to localise the 3D poses within a global coordinate system accurately reconstructing the scene in real-time.
Knap, Pawel
90d354cb-ed95-4027-8c95-0b736fe66207
Hardy, Peter
361a5d48-51cf-4eaf-9b60-1de78f2f2f20
Tamajo, Alberto
190a4680-7aa4-4d37-82b9-e03b96c5965f
Lim, Hwasup
3c9f6a38-639d-4c4c-afc2-a0704166d72e
Kim, Hansung
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Knap, Pawel
90d354cb-ed95-4027-8c95-0b736fe66207
Hardy, Peter
361a5d48-51cf-4eaf-9b60-1de78f2f2f20
Tamajo, Alberto
190a4680-7aa4-4d37-82b9-e03b96c5965f
Lim, Hwasup
3c9f6a38-639d-4c4c-afc2-a0704166d72e
Kim, Hansung
2c7c135c-f00b-4409-acb2-85b3a9e8225f

Knap, Pawel, Hardy, Peter, Tamajo, Alberto, Lim, Hwasup and Kim, Hansung (2023) Real-time omnidirectional 3D multi-person human pose estimation with occlusion handling. ACM SIGGRAPH European Conference on Visual Media Production, BFI Southban, London, United Kingdom. 30 Nov - 01 Dec 2023.

Record type: Conference or Workshop Item (Poster)

Abstract

We present a multi-person 3D human pose estimation system that addresses a major limitation in existing models, namely the focus on single person pose estimation. By using an off-the-shelf 2D detectors and 2D-3D lifting model, we first obtain the 3D poses of detected individuals in theirown local coordinate system from video. We then use a radar sensing data and people-matching approach to localise the 3D poses within a global coordinate system accurately reconstructing the scene in real-time.

Text
127_23CVMP-Pawel - Accepted Manuscript
Download (1MB)

More information

Published date: 30 November 2023
Venue - Dates: ACM SIGGRAPH European Conference on Visual Media Production, BFI Southban, London, United Kingdom, 2023-11-30 - 2023-12-01

Identifiers

Local EPrints ID: 490632
URI: http://eprints.soton.ac.uk/id/eprint/490632
PURE UUID: 0c9909ef-f8e3-4252-b345-e441d5658f5f
ORCID for Alberto Tamajo: ORCID iD orcid.org/0000-0002-0881-7918
ORCID for Hansung Kim: ORCID iD orcid.org/0000-0003-4907-0491

Catalogue record

Date deposited: 31 May 2024 16:48
Last modified: 01 Jun 2024 02:07

Export record

Contributors

Author: Pawel Knap
Author: Peter Hardy
Author: Alberto Tamajo ORCID iD
Author: Hwasup Lim
Author: Hansung Kim ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×