DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Person Identification by Footstep Sound Using Convolutional Neural Networks

Algermissen, Stephan and Hörnlein, Max (2021) Person Identification by Footstep Sound Using Convolutional Neural Networks. Applied Mechanics, 2 (2), pp. 257-273. Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/applmech2020016. ISSN 2673-3161.

[img] PDF - Published version

Official URL: https://www.mdpi.com/2673-3161/2/2/16


Human gait is very individual and it may serve as biometric to identify people in camera recordings. Comparable results can be achieved while using the acoustic signature of human footstep sounds. This acoustic solution offers the opportunity of less installation space and the use of cost-efficient microphones when compared to visual system. In this paper, a method for person identification based on footstep sounds is proposed. First, step sounds are isolated from microphone recordings and separated into 500 ms samples. The samples are transformed with a sliding window into mel-frequency cepstral coefficients (MFCC). The result is represented as an image that serves as input to a convolutional neural network (CNN). The dataset for training and validating the CNN is recorded with five subjects in the acoustic lab of DLR. These experiments identify a total number of 1125 steps. The validation of the CNN reveals a minimum F1-score of 0.94 for all five classes and an accuracy of 0.98. The Grad-CAM method is applied to visualize the background of its decision in order to verify the functionality of the proposed CNN. Subsequently, two challenges for practical implementations, noise and different footwear, are discussed using experimental data.

Item URL in elib:https://elib.dlr.de/142741/
Document Type:Article
Title:Person Identification by Footstep Sound Using Convolutional Neural Networks
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Algermissen, StephanUNSPECIFIEDhttps://orcid.org/0000-0002-0507-8195UNSPECIFIED
Date:11 May 2021
Journal or Publication Title:Applied Mechanics
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In ISI Web of Science:No
Page Range:pp. 257-273
Publisher:Multidisciplinary Digital Publishing Institute (MDPI)
Keywords:person identification; convolutional neural networks; MFCC; gait recognition; machine learning
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Aeronautics
HGF - Program Themes:other
DLR - Research area:Aeronautics
DLR - Program:L - no assignment
DLR - Research theme (Project):L - no assignment
Location: Braunschweig
Institutes and Institutions:Institute of Composite Structures and Adaptive Systems > Adaptronics
Deposited By: Algermissen, Dr.-Ing. Stephan
Deposited On:21 Jun 2021 08:52
Last Modified:23 Oct 2023 09:50

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.