RO  EN
IMI/Publicaţii/CSJM/Ediţii/CSJM v.33, n.2 (98), 2025/

Enhancing Gait Recognition with Attention-Based Spatial-Temporal Deep Learning: The GaitDeep Framework

Authors: S. Mandlik, R. Labade, S. Chaudhari, B. Agarkar
Keywords: Deep learning, Gait Recognition, Biometric, Spatial-temporal refinement.

Abstract

Gait, an individual’s unique walking style, serves as an effective biometric tool for surveillance. Unlike fingerprints or iris scans, gait is observable from a distance without the subject’s awareness, making it ideal for security applications. CNNs struggle with video variability, affecting gait recognition. This study introduces GaitDeep, a spatial-temporal refinement using a deep dense network. It integrates attention-enhanced spatial extraction with a two-directional LSTM-based temporal module to prioritize key segments. Evaluated on the OU-ISIR, OU-MVLP, and CASIA-B datasets, GaitDeep achieves accuracies of 95.1\%, 0.96\%, and 98.10\%, respectively, outperforming state-of-the-art methods and establishing a new benchmark for gait recognition.

Department of E&TC Engineering, Sanjivani College of Engineering,
Kopargaon, India, Savitribai Phule Pune University, Pune, India.

Sachin Mandlik
ORCID: https://orcid.org/0000-0002-7097-8253
E-mail:

Rekha Labade
ORCID: https://orcid.org/0000-0001-9461-5361
E-mail:

Sachin Chaudhari
ORCID: https://orcid.org/0009-0005-8856-8905
E-mail:

Balasaheb Agarkar
ORCID: https://orcid.org/0000-0002-2775-8095
E-mail:

DOI

https://doi.org/10.56415/csjm.v33.10

Fulltext

Adobe PDF document – 1.75 Mb