Skip to Main content Skip to Navigation
Conference papers

3D Human Poses Estimation from a single 2D silhouette

Fabrice Atrevi 1 Damien Vivet Florent Duculty 2 Bruno Emile 3
1 Pôle IRAuS - Axe Images et Vision
PRISME - Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique
2 Pôle IRAuS, Autom
PRISME - Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique
3 Pôle IRAuS ; Axe Images et Vision
PRISME - Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique
Abstract : This work focuses on the problem of automatically extracting human 3D poses from a single 2D image. By pose we mean the configuration of human bones in order to reconstruct a 3D skeleton representing the 3D posture of the detected human. This problem is highly non-linear in nature and confounds standard regression techniques. Our approach combines prior learned correspondences between silhouettes and skeletons extracted from 3D human models. In order to match detected silhouettes with simulated silhouettes, we used Krawtchouk geometric moment as shape descriptor. We provide quantitative results for image retrieval across different action and subjects, captured from differing viewpoints. We show that our approach gives promising result for 3D pose extraction from a single silhouette.
Document type :
Conference papers
Complete list of metadata

Cited literature [29 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01636974
Contributor : Damien Vivet <>
Submitted on : Friday, November 17, 2017 - 11:06:46 AM
Last modification on : Monday, August 16, 2021 - 4:26:01 PM
Long-term archiving on: : Sunday, February 18, 2018 - 1:33:19 PM

File

VISAPP_HumanPoseEstimation.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Fabrice Atrevi, Damien Vivet, Florent Duculty, Bruno Emile. 3D Human Poses Estimation from a single 2D silhouette. 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Feb 2016, Rome, Italy. ⟨10.5220/0005711503610369⟩. ⟨hal-01636974⟩

Share

Metrics

Record views

306

Files downloads

1478