Cargando…

An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking

Estimating accurate 3D human poses from 2D images remains a challenge due to the lack of explicit depth information in 2D data. This paper proposes an improved mixture density network for 3D human pose estimation called the Locally Connected Mixture Density Network (LCMDN). Instead of conducting dir...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Yiqi, Ma, Shichao, Zhang, Dejun, Huang, Weilun, Chen, Yilin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9269848/
https://www.ncbi.nlm.nih.gov/pubmed/35808480
http://dx.doi.org/10.3390/s22134987
_version_ 1784744322626748416
author Wu, Yiqi
Ma, Shichao
Zhang, Dejun
Huang, Weilun
Chen, Yilin
author_facet Wu, Yiqi
Ma, Shichao
Zhang, Dejun
Huang, Weilun
Chen, Yilin
author_sort Wu, Yiqi
collection PubMed
description Estimating accurate 3D human poses from 2D images remains a challenge due to the lack of explicit depth information in 2D data. This paper proposes an improved mixture density network for 3D human pose estimation called the Locally Connected Mixture Density Network (LCMDN). Instead of conducting direct coordinate regression or providing unimodal estimates per joint, our approach predicts multiple possible hypotheses by the Mixture Density Network (MDN). Our network can be divided into two steps: the 2D joint points are estimated from the input images first; then, the information of human joints correlation is extracted by a feature extractor. After the human pose feature is extracted, multiple pose hypotheses are generated via the hypotheses generator. In addition, to make better use of the relationship between human joints, we introduce the Locally Connected Network (LCN) as a generic formulation to replace the traditional Fully Connected Network (FCN), which is applied to a feature extraction module. Finally, to select the most appropriate 3D pose result, a 3D pose selector based on the ordinal ranking of joints is adopted to score the predicted pose. The LCMDN improves the representation capability and robustness of the original MDN method notably. Experiments are conducted on the Human3.6M and MPII dataset. The average Mean Per Joint Position Error (MPJPE) of our proposed LCMDN reaches 50 mm on the Human3.6M dataset, which is on par or better than the state-of-the-art works. The qualitative results on the MPII dataset show that our network has a strong generalization ability.
format Online
Article
Text
id pubmed-9269848
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-92698482022-07-09 An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking Wu, Yiqi Ma, Shichao Zhang, Dejun Huang, Weilun Chen, Yilin Sensors (Basel) Article Estimating accurate 3D human poses from 2D images remains a challenge due to the lack of explicit depth information in 2D data. This paper proposes an improved mixture density network for 3D human pose estimation called the Locally Connected Mixture Density Network (LCMDN). Instead of conducting direct coordinate regression or providing unimodal estimates per joint, our approach predicts multiple possible hypotheses by the Mixture Density Network (MDN). Our network can be divided into two steps: the 2D joint points are estimated from the input images first; then, the information of human joints correlation is extracted by a feature extractor. After the human pose feature is extracted, multiple pose hypotheses are generated via the hypotheses generator. In addition, to make better use of the relationship between human joints, we introduce the Locally Connected Network (LCN) as a generic formulation to replace the traditional Fully Connected Network (FCN), which is applied to a feature extraction module. Finally, to select the most appropriate 3D pose result, a 3D pose selector based on the ordinal ranking of joints is adopted to score the predicted pose. The LCMDN improves the representation capability and robustness of the original MDN method notably. Experiments are conducted on the Human3.6M and MPII dataset. The average Mean Per Joint Position Error (MPJPE) of our proposed LCMDN reaches 50 mm on the Human3.6M dataset, which is on par or better than the state-of-the-art works. The qualitative results on the MPII dataset show that our network has a strong generalization ability. MDPI 2022-07-01 /pmc/articles/PMC9269848/ /pubmed/35808480 http://dx.doi.org/10.3390/s22134987 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wu, Yiqi
Ma, Shichao
Zhang, Dejun
Huang, Weilun
Chen, Yilin
An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking
title An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking
title_full An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking
title_fullStr An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking
title_full_unstemmed An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking
title_short An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking
title_sort improved mixture density network for 3d human pose estimation with ordinal ranking
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9269848/
https://www.ncbi.nlm.nih.gov/pubmed/35808480
http://dx.doi.org/10.3390/s22134987
work_keys_str_mv AT wuyiqi animprovedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT mashichao animprovedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT zhangdejun animprovedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT huangweilun animprovedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT chenyilin animprovedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT wuyiqi improvedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT mashichao improvedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT zhangdejun improvedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT huangweilun improvedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking
AT chenyilin improvedmixturedensitynetworkfor3dhumanposeestimationwithordinalranking