Improving Small-Scale Human Action Recognition Performance Using a 3D Heatmap Volume
Sensors · 2023
DOI: 10.3390/s23146364 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Lin Yuan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China. Hauptthemen laut MEDLINE: Pattern Recognition, Automated, Human Activities. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
In recent years, skeleton-based human action recognition has garnered significant research attention, with proposed recognition or segmentation methods typically validated on large-scale coarse-grained action datasets. However, there remains a lack of research on the recognition of small-scale fine-grained human actions using deep learning methods, which have greater practical significance. To address this gap, we propose a novel approach based on heatmap-based pseudo videos and a unified, general model applicable to all modality datasets. Leveraging anthropometric kinematics as prior information, we extract common human motion features among datasets through an ad hoc pre-trained model. To overcome joint mismatch issues, we partition the human skeleton into five parts, a simple yet effective technique for information sharing. Our approach is evaluated on two datasets, including the public Nursing Activities and our self-built Tai Chi Action dataset. Results from linear evaluation protocol and fine-tuned evaluation demonstrate that our pre-trained model effectively captures common motion features among human actions and achieves steady and precise accuracy across all training settings, while mitigating network overfitting. Notably, our model outperforms state-of-the-art models in recognition accuracy when fusing joint and limb modality features along the channel dimension.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China.
ORCID-Profile: Qiang Wang, Leiyang Xu
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yuan, L., He, Z., Wang, Q., Xu, L., & Ma, X. (2023). Improving Small-Scale Human Action Recognition Performance Using a 3D Heatmap Volume. Sensors. https://doi.org/10.3390/s23146364
Vancouver
Yuan L, He Z, Wang Q, Xu L, Ma X. Improving Small-Scale Human Action Recognition Performance Using a 3D Heatmap Volume. Sensors. 2023. doi:10.3390/s23146364
BibTeX
@article{Yuan2023,
author = {Yuan, Lin and He, Zhen and Wang, Qiang and Xu, Leiyang and Ma, Xiang},
title = {Improving Small-Scale Human Action Recognition Performance Using a 3D Heatmap Volume},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23146364}
}
EUVIMED