Absolute Human Pose Estimation with Depth Prediction Network

Marton Veges, Andras Lorincz

Research output: Conference contribution

Abstract

The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.

Original languageEnglish
Title of host publication2019 International Joint Conference on Neural Networks, IJCNN 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728119854
DOIs
Publication statusPublished - júl. 2019
Event2019 International Joint Conference on Neural Networks, IJCNN 2019 - Budapest, Hungary
Duration: júl. 14 2019júl. 19 2019

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2019-July

Conference

Conference2019 International Joint Conference on Neural Networks, IJCNN 2019
CountryHungary
CityBudapest
Period7/14/197/19/19

Fingerprint

Cameras
Neural networks
Processing

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Veges, M., & Lorincz, A. (2019). Absolute Human Pose Estimation with Depth Prediction Network. In 2019 International Joint Conference on Neural Networks, IJCNN 2019 [8852387] (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2019.8852387

Absolute Human Pose Estimation with Depth Prediction Network. / Veges, Marton; Lorincz, Andras.

2019 International Joint Conference on Neural Networks, IJCNN 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8852387 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July).

Research output: Conference contribution

Veges, M & Lorincz, A 2019, Absolute Human Pose Estimation with Depth Prediction Network. in 2019 International Joint Conference on Neural Networks, IJCNN 2019., 8852387, Proceedings of the International Joint Conference on Neural Networks, vol. 2019-July, Institute of Electrical and Electronics Engineers Inc., 2019 International Joint Conference on Neural Networks, IJCNN 2019, Budapest, Hungary, 7/14/19. https://doi.org/10.1109/IJCNN.2019.8852387
Veges M, Lorincz A. Absolute Human Pose Estimation with Depth Prediction Network. In 2019 International Joint Conference on Neural Networks, IJCNN 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8852387. (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2019.8852387
Veges, Marton ; Lorincz, Andras. / Absolute Human Pose Estimation with Depth Prediction Network. 2019 International Joint Conference on Neural Networks, IJCNN 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings of the International Joint Conference on Neural Networks).
@inproceedings{80398ac096d74fc0bcb24c867c567de8,
title = "Absolute Human Pose Estimation with Depth Prediction Network",
abstract = "The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.",
keywords = "absolute pose estimation, depth prediction, global coordinates, human pose estimation",
author = "Marton Veges and Andras Lorincz",
year = "2019",
month = "7",
doi = "10.1109/IJCNN.2019.8852387",
language = "English",
series = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 International Joint Conference on Neural Networks, IJCNN 2019",

}

TY - GEN

T1 - Absolute Human Pose Estimation with Depth Prediction Network

AU - Veges, Marton

AU - Lorincz, Andras

PY - 2019/7

Y1 - 2019/7

N2 - The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.

AB - The common approach to 3D human pose estimation is predicting the body joint coordinates relative to the hip. This works well for a single person but is insufficient in the case of multiple interacting people. Methods predicting absolute coordinates first estimate a root-relative pose then calculate the translation via a secondary optimization task. We propose a neural network that predicts joints in a camera centered coordinate system instead of a root-relative one. Unlike previous methods, our network works in a single step without any post-processing. Our network beats previous methods on the MuPoTS-3D dataset and achieves state-of-the-art results.

KW - absolute pose estimation

KW - depth prediction

KW - global coordinates

KW - human pose estimation

UR - http://www.scopus.com/inward/record.url?scp=85073191522&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073191522&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2019.8852387

DO - 10.1109/IJCNN.2019.8852387

M3 - Conference contribution

AN - SCOPUS:85073191522

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2019 International Joint Conference on Neural Networks, IJCNN 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -