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
30 November 2023
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
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
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
Author:
Hwasup Lim
Author:
Hansung Kim
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