Gait-CNN-ViT: Multi-Model Gait Recognition with Convolutional Neural Networks and Vision Transformer
Sensors · 07.04.2023 · 23 (8) · 3809
DOI: 10.3390/s23083809 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 07.04.2023. Verfasst von Jashila Nair Mogan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia. Hauptthemen laut MEDLINE: Neural Networks, Computer, Machine Learning. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Higher Education, Multimedia University, Yayasan Universiti Multimedia.
Abstract (Originalsprache)
Gait recognition, the task of identifying an individual based on their unique walking style, can be difficult because walking styles can be influenced by external factors such as clothing, viewing angle, and carrying conditions. To address these challenges, this paper proposes a multi-model gait recognition system that integrates Convolutional Neural Networks (CNNs) and Vision Transformer. The first step in the process is to obtain a gait energy image, which is achieved by applying an averaging technique to a gait cycle. The gait energy image is then fed into three different models, DenseNet-201, VGG-16, and a Vision Transformer. These models are pre-trained and fine-tuned to encode the salient gait features that are specific to an individual’s walking style. Each model provides prediction scores for the classes based on the encoded features, and these scores are then summed and averaged to produce the final class label. The performance of this multi-model gait recognition system was evaluated on three datasets, CASIA-B, OU-ISIR dataset D, and OU-ISIR Large Population dataset. The experimental results showed substantial improvement compared to existing methods on all three datasets. The integration of CNNs and ViT allows the system to learn both the pre-defined and distinct features, providing a robust solution for gait recognition even under the influence of covariates.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia.
- Department of Computer Science, King Khalid University, Abha 61421, Saudi Arabia.
- Center for Artificial Intelligence (CAI), King Khalid University, Abha 61421, Saudi Arabia.
ORCID-Profile: Jashila Nair Mogan, Chin Poo Lee, Kian Ming Lim, Mohammed Ali, Ali Alqahtani
Förderung
- Ministry of Higher Education
- Multimedia University
- Yayasan Universiti Multimedia
- Fundamental Research Grant Scheme of the Ministry of Higher Education
- Deanship of Scientific Research, King Khalid University, Saudi Arabia
- Multimedia University Internal Research Grant
Zitieren
APA
Mogan, J. N., Lee, C. P., Lim, K. M., Ali, M., & Alqahtani, A. (2023). Gait-CNN-ViT: Multi-Model Gait Recognition with Convolutional Neural Networks and Vision Transformer. Sensors, 23(8), 3809. https://doi.org/10.3390/s23083809
Vancouver
Mogan JN, Lee CP, Lim KM, Ali M, Alqahtani A. Gait-CNN-ViT: Multi-Model Gait Recognition with Convolutional Neural Networks and Vision Transformer. Sensors. 2023;23(8):3809. doi:10.3390/s23083809
BibTeX
@article{Mogan2023,
author = {Mogan, Jashila Nair and Lee, Chin Poo and Lim, Kian Ming and Ali, Mohammed and Alqahtani, Ali},
title = {Gait-CNN-ViT: Multi-Model Gait Recognition with Convolutional Neural Networks and Vision Transformer},
journal = {Sensors},
year = {2023},
volume = {23},
number = {8},
pages = {3809},
doi = {10.3390/s23083809}
}
EUVIMED