Structuring Variability in Human Gait Datasets: A Covariate-Centered Taxonomy and Systematic Review of Image- and Depth-Based Collections

Nunes, João Ferreira; Moreira, Pedro Miguel; Tavares, João Manuel R. S.

doi:10.3390/jimaging12070334

Open AccessSystematic Review

Structuring Variability in Human Gait Datasets: A Covariate-Centered Taxonomy and Systematic Review of Image- and Depth-Based Collections

by

João Ferreira Nunes

^1,*

,

Pedro Miguel Moreira

¹

and

João Manuel R. S. Tavares

²

¹

ADiT-Lab, Instituto Politécnico de Viana do Castelo, 4900-347 Viana do Castelo, Portugal

²

Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial, Departamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, 4200-465 Porto, Portugal

^*

Author to whom correspondence should be addressed.

J. Imaging 2026, 12(7), 334; https://doi.org/10.3390/jimaging12070334

Submission received: 5 June 2026 / Revised: 13 July 2026 / Accepted: 16 July 2026 / Published: 22 July 2026

(This article belongs to the Section Computer Vision and Pattern Recognition)

Download

Browse Figures

Versions Notes

Abstract

Human gait datasets play a central role in the development and evaluation of computer vision models. However, the current dataset landscape remains highly heterogeneous, with inconsistent reporting of acquisition conditions, user variability, and sensing configurations, which limits reproducibility and hinders principled cross-dataset comparability. In this work, we propose a covariate-centered, modality-agnostic taxonomy for gait datasets, explicitly structuring variability across scene-level, user-level, and sensor-level factors. The proposed framework enables consistent characterization of datasets through a standardized set of covariates (A–R), bridging differences across application domains and sensing modalities. Following a systematic review protocol aligned with PRISMA 2020, we analyze 47 publicly available image- and depth-based human gait datasets spanning healthcare, biometric, and attribute-recognition application domains. Using the proposed taxonomy, we derive a quantitative analysis of covariate coverage, revealing systematic biases in current dataset design.

Keywords: gait analysis; dataset review; RGB; RGB-D; depth; taxonomy; covariates; benchmarking; computer vision

Share and Cite

MDPI and ACS Style

Nunes, J.F.; Moreira, P.M.; Tavares, J.M.R.S. Structuring Variability in Human Gait Datasets: A Covariate-Centered Taxonomy and Systematic Review of Image- and Depth-Based Collections. J. Imaging 2026, 12, 334. https://doi.org/10.3390/jimaging12070334

AMA Style

Nunes JF, Moreira PM, Tavares JMRS. Structuring Variability in Human Gait Datasets: A Covariate-Centered Taxonomy and Systematic Review of Image- and Depth-Based Collections. Journal of Imaging. 2026; 12(7):334. https://doi.org/10.3390/jimaging12070334

Chicago/Turabian Style

Nunes, João Ferreira, Pedro Miguel Moreira, and João Manuel R. S. Tavares. 2026. "Structuring Variability in Human Gait Datasets: A Covariate-Centered Taxonomy and Systematic Review of Image- and Depth-Based Collections" Journal of Imaging 12, no. 7: 334. https://doi.org/10.3390/jimaging12070334

APA Style

Nunes, J. F., Moreira, P. M., & Tavares, J. M. R. S. (2026). Structuring Variability in Human Gait Datasets: A Covariate-Centered Taxonomy and Systematic Review of Image- and Depth-Based Collections. Journal of Imaging, 12(7), 334. https://doi.org/10.3390/jimaging12070334

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Structuring Variability in Human Gait Datasets: A Covariate-Centered Taxonomy and Systematic Review of Image- and Depth-Based Collections

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI