Abstract

With advancements in biometric securities, focus has increased on utilizing gait as a means of recognition. Gait describes the unique walking pattern present in humans and has shown promising results in person re-identification tasks. Unlike other biometric features, gait is unique in that it is a subconscious behavior minimizing the risk of purposeful obfuscation. In this research, we first cover supervised approaches showing that current methods fail to learn a unique signature that describes the motion of a subject. Rather they extract frame-based feature information which is then aggregated. While these methods have shown to be effective, they do not solve the underlying problem of trying to extract a gait signature. In this research, a novel approach is proposed that utilizes motion information to extract a true gait signature. Utilizing the repetitive nature of body part motion, we argue that since each subject has a unique gait, they will also have a unique repetition pattern. From a walking sequence, we are able to extract a frame-based similarity matrix that effectively shows a unique repetitive pattern. We further explore this idea using unsupervised learning and show that this unique repetition pattern performs well in both multi-view and cross-covariate scenarios. Currently there are no unsupervised methods for gait recognition, so this foundational work acts as a guideline for future research and evaluation. In addition, the proposed unsupervised method outperforms many supervised methods.

Notes

If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at STARS@ucf.edu

Graduation Date

2021

Semester

Spring

Advisor

Rawat, Yogesh Singh

Degree

Master of Science (M.S.)

College

College of Engineering and Computer Science

Department

Computer Science

Degree Program

Computer Science

Format

application/pdf

Identifier

CFE0008498; DP0024174

URL

https://purls.library.ucf.edu/go/DP0024174

Language

English

Release Date

May 2021

Length of Campus-only Access

None

Access Status

Masters Thesis (Open Access)

Download

Share

COinS