A View-invariant Framework for Fast Skeleton-based Action Recognition using a Single RGB Camera

Enjie Ghorbel, Konstantinos Papadopoulos, Renato Baptista, Himadri Pathak, Girum Demisse, Djamila Aouada, Björn Ottersten

2019

Abstract

View-invariant action recognition using a single RGB camera represents a very challenging topic due to the lack of 3D information in RGB images. Lately, the recent advances in deep learning made it possible to extract a 3D skeleton from a single RGB image. Taking advantage of this impressive progress, we propose a simple framework for fast and view-invariant action recognition using a single RGB camera. The proposed pipeline can be seen as the association of two key steps. The first step is the estimation of a 3D skeleton from a single RGB image using a CNN-based pose estimator such as VNect. The second one aims at computing view-invariant skeleton-based features based on the estimated 3D skeletons. Experiments are conducted on two well-known benchmarks, namely, IXMAS and Northwestern-UCLA datasets. The obtained results prove the validity of our concept, which suggests a new way to address the challenge of RGB-based view-invariant action recognition.

Paper Citation

in Harvard Style

Ghorbel E., Papadopoulos K., Baptista R., Pathak H., Demisse G., Aouada D. and Ottersten B. (2019). A View-invariant Framework for Fast Skeleton-based Action Recognition using a Single RGB Camera. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 573-582. DOI: 10.5220/0007524405730582

in Bibtex Style

@conference{visapp19,
author={Enjie Ghorbel and Konstantinos Papadopoulos and Renato Baptista and Himadri Pathak and Girum Demisse and Djamila Aouada and Björn Ottersten},
title={A View-invariant Framework for Fast Skeleton-based Action Recognition using a Single RGB Camera},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={573-582},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007524405730582},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - A View-invariant Framework for Fast Skeleton-based Action Recognition using a Single RGB Camera
SN - 978-989-758-354-4
AU - Ghorbel E.
AU - Papadopoulos K.
AU - Baptista R.
AU - Pathak H.
AU - Demisse G.
AU - Aouada D.
AU - Ottersten B.
PY - 2019
SP - 573
EP - 582
DO - 10.5220/0007524405730582
PB - SciTePress