What question did this study set out to answer?

The aim is to develop a robust gait identification method that operates effectively in various real-world conditions.

Enabling Passive Gait Identification in Realistic and Uncontrolled Environments Using Deep Learning and Spatiotemporal Biometrics

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates a novel method for accurate gait identification in real-world environments, suggesting broad applications in security and healthcare.

The aim is to develop a robust gait identification method that operates effectively in various real-world conditions.
Introduced spatiotemporal kinematics‐informed gait identification (STONI‐GID) method
Utilized human pose and occlusion state estimation
Employed deep machine learning techniques for analysis
Evaluated performance on primary dataset of 65 participants and larger datasets
Achieved identification accuracy of up to 98.66% on primary dataset
Outperformed existing methods with accuracies of 97.68% on the Southampton dataset and 99.12% on GRIDDS

Topham et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Demonstrates a novel method for accurate gait identification in real-world environments, suggesting broad applications in security and healthcare.

The aim is to develop a robust gait identification method that operates effectively in various real-world conditions.
Introduced spatiotemporal kinematics‐informed gait identification (STONI‐GID) method
Utilized human pose and occlusion state estimation
Employed deep machine learning techniques for analysis
Evaluated performance on primary dataset of 65 participants and larger datasets
Achieved identification accuracy of up to 98.66% on primary dataset
Outperformed existing methods with accuracies of 97.68% on the Southampton dataset and 99.12% on GRIDDS

Topham et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark