Advances in Vision-Based Gait Recognition: From Handcrafted to Deep Learning
Overview
Affiliations
Identifying people's identity by using behavioral biometrics has attracted many researchers' attention in the biometrics industry. Gait is a behavioral trait, whereby an individual is identified based on their walking style. Over the years, gait recognition has been performed by using handcrafted approaches. However, due to several covariates' effects, the competence of the approach has been compromised. Deep learning is an emerging algorithm in the biometrics field, which has the capability to tackle the covariates and produce highly accurate results. In this paper, a comprehensive overview of the existing deep learning-based gait recognition approach is presented. In addition, a summary of the performance of the approach on different gait datasets is provided.
Wu C, Tsai C, Wu F, Chiang C, Chiou J Biomimetics (Basel). 2025; 10(2).
PMID: 39997101 PMC: 11853110. DOI: 10.3390/biomimetics10020079.
Song C, Yun L, Li R Sensors (Basel). 2024; 24(17).
PMID: 39275411 PMC: 11397920. DOI: 10.3390/s24175500.
A hybrid human recognition framework using machine learning and deep neural networks.
Sheneamer A, Halawi M, Al-Qahtani M PLoS One. 2024; 19(6):e0300614.
PMID: 38905186 PMC: 11192334. DOI: 10.1371/journal.pone.0300614.
Gait-ViT: Gait Recognition with Vision Transformer.
Mogan J, Lee C, Lim K, Muthu K Sensors (Basel). 2022; 22(19).
PMID: 36236462 PMC: 9572525. DOI: 10.3390/s22197362.
Detecting Gait Events from Accelerations Using Reservoir Computing.
Chiasson-Poirier L, Younesian H, Turcot K, Sylvestre J Sensors (Basel). 2022; 22(19).
PMID: 36236278 PMC: 9570885. DOI: 10.3390/s22197180.