A Survey on 3D Skeleton-Based Action Recognition Using Learning Method
Cyborg and Bionic Systems · 2024-01 · 5
DOI: 10.34133/cbsystems.0100 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cyborg and Bionic Systems, online erschienen am 16.05.2024. Verfasst von Bin Ren und 3 weiteren Autor:innen. Beteiligte Einrichtung: University of Pisa, Pisa, Italy. Die Arbeit wurde bisher 154-mal zitiert (Crossref) und nennt 153 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shenzhen Municipality.
Abstract (Originalsprache)
Three-dimensional skeleton-based action recognition (3D SAR) has gained important attention within the computer vision community, owing to the inherent advantages offered by skeleton data. As a result, a plethora of impressive works, including those based on conventional handcrafted features and learned feature extraction methods, have been conducted over the years. However, prior surveys on action recognition have primarily focused on video or red-green-blue (RGB) data-dominated approaches, with limited coverage of reviews related to skeleton data. Furthermore, despite the extensive application of deep learning methods in this field, there has been a notable absence of research that provides an introductory or comprehensive review from the perspective of deep learning architectures. To address these limitations, this survey first underscores the importance of action recognition and emphasizes the significance of 3-dimensional (3D) skeleton data as a valuable modality. Subsequently, we provide a comprehensive introduction to mainstream action recognition techniques based on 4 fundamental deep architectures, i.e., recurrent neural networks, convolutional neural networks, graph convolutional network, and Transformers. All methods with the corresponding architectures are then presented in a data-driven manner with detailed discussion. Finally, we offer insights into the current largest 3D skeleton dataset, NTU-RGB+D, and its new edition, NTU-RGB+D 120, along with an overview of several top-performing algorithms on these datasets. To the best of our knowledge, this research represents the first comprehensive discussion of deep learning-based action recognition using 3D skeleton data.
Autor:innen und Institutionen
- University of Pisa, Pisa, Italy.
- University of Trento, Trento, Italy.
- National Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China.
- Peng Cheng Laboratory, Shenzhen, China.
ORCID-Profile: Bin Ren
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shenzhen Municipality
Zitieren
APA
Ren, B., Liu, M., Ding, R., & Liu, H. (2024). A Survey on 3D Skeleton-Based Action Recognition Using Learning Method. Cyborg and Bionic Systems, 5. https://doi.org/10.34133/cbsystems.0100
Vancouver
Ren B, Liu M, Ding R, Liu H. A Survey on 3D Skeleton-Based Action Recognition Using Learning Method. Cyborg and Bionic Systems. 2024;5. doi:10.34133/cbsystems.0100
BibTeX
@article{Ren2024,
author = {Ren, Bin and Liu, Mengyuan and Ding, Runwei and Liu, Hong},
title = {A Survey on 3D Skeleton-Based Action Recognition Using Learning Method},
journal = {Cyborg and Bionic Systems},
year = {2024},
volume = {5},
doi = {10.34133/cbsystems.0100}
}
EUVIMED