Version 1
: Received: 28 January 2024 / Approved: 29 January 2024 / Online: 29 January 2024 (08:19:58 CET)
Version 2
: Received: 18 February 2024 / Approved: 20 February 2024 / Online: 21 February 2024 (03:46:16 CET)
Version 3
: Received: 25 July 2024 / Approved: 25 July 2024 / Online: 26 July 2024 (04:29:00 CEST)
How to cite:
Abduljalil, H.; Elhayek, A.; Marish Ali, A.; Alsolami, F. Spatiotemporal Graph Autoencoder Network for Skeleton-Based Human Action Recognition. Preprints2024, 2024011998. https://doi.org/10.20944/preprints202401.1998.v3
Abduljalil, H.; Elhayek, A.; Marish Ali, A.; Alsolami, F. Spatiotemporal Graph Autoencoder Network for Skeleton-Based Human Action Recognition. Preprints 2024, 2024011998. https://doi.org/10.20944/preprints202401.1998.v3
Abduljalil, H.; Elhayek, A.; Marish Ali, A.; Alsolami, F. Spatiotemporal Graph Autoencoder Network for Skeleton-Based Human Action Recognition. Preprints2024, 2024011998. https://doi.org/10.20944/preprints202401.1998.v3
APA Style
Abduljalil, H., Elhayek, A., Marish Ali, A., & Alsolami, F. (2024). Spatiotemporal Graph Autoencoder Network for Skeleton-Based Human Action Recognition. Preprints. https://doi.org/10.20944/preprints202401.1998.v3
Chicago/Turabian Style
Abduljalil, H., Abdullah Marish Ali and Fawaz Alsolami. 2024 "Spatiotemporal Graph Autoencoder Network for Skeleton-Based Human Action Recognition" Preprints. https://doi.org/10.20944/preprints202401.1998.v3
Abstract
The task of human action recognition (HAR) based on skeleton data is a challenging yet crucial technique owing to its wide-ranging applications in numerous domains, including patient monitoring, security surveillance, and observation of human-machine interactions. While numerous algorithms have been proposed in an attempt to distinguish between a myriad of activities, most practical applications necessitate highly accurate detection of specific activity types. This study proposes a novel and highly accurate spatiotemporal graph autoencoder network for HAR based on skeleton data. Furthermore, an extensive investigation was conducted employing diverse modalities. To this end, a spatiotemporal graph autoencoder was constructed to automatically learn both spatial and temporal patterns from human skeleton datasets. The powerful graph convolutional network, designated as GA-GCN, developed in this study, notably outperforms the majority of existing state-of-the-art methods when evaluated on two common datasets, namely NTU RGB+D and NTU RGB+D 120. On the first dataset, the proposed approach achieved accuracies of 92.3\% and 96.8\% for the cross-subject and cross-view evaluations, respectively. On the more challenging NTU RGB+D 120 dataset, GA-GCN attained accuracies of 88.8\% and 90.4\% for the cross-subject and cross-set evaluations, respectively.
Keywords
graph convolutional networks; graph autoencoder; deep learning; human activity analysis; skeleton-based human action recognition
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.