Understanding the Gap between 2D and 3D Skeleton-Based Action Recognition

Investor logo

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

ELIÁŠ Petr SEDMIDUBSKÝ Jan ZEZULA Pavel

Year of publication 2019
Type Article in Proceedings
Conference 21st IEEE International Symposium on Multimedia (ISM)
MU Faculty or unit

Faculty of Informatics

Citation
Doi http://dx.doi.org/10.1109/ISM46123.2019.00041
Keywords 2D skeleton data;3D skeleton data;action recognition;LSTM;motion data understanding
Description Large volumes of RGB video data are recorded and processed every day. One of the embedded data modality within these videos is the information about human motions. Up to now, this information has been almost unfeasible to extract, and thus human-motion understanding research has been mainly limited to 3D skeleton data captured by dedicated hardware only. However, with recent advances in computer vision, it is possible to estimate 2D skeleton sequences from ordinary videos quite accurately. Such 2D skeleton data possess an excellent potential for future motion understanding applications. In this paper, we adopt a state-of-the-art bidirectional LSTM network to analyze the accuracy gap in the expressive power of 2D and 3D skeleton data recorded simultaneously on a high number of 20k human actions. We further examine how the missing depth information and fluctuations in 2D skeleton sizes influence the recognition rate. We also demonstrate the suitability of 2D skeleton data for general daily activity recognition by reporting baselines on the PKU-MMD dataset.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.