Spatial footstep recognition by convolutional neural networks for biometrie applications

  • Omar Costilla-Reyes
  • , Ruben Vera-Rodriguez
  • , Patricia Scully
  • , Krikor B. Ozanyan

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

12 Citations (Scopus)

Abstract

We propose a Convolutional Neural Network model to learn spatial footstep features end-to-end from a floor sensor system for biometric applications. Our model's generalization performance is assessed by independent validation and evaluation datasets from the largest footstep database to date, containing nearly 20,000 footstep signals from 127 users. We report footstep recognition performance as Equal Error Rate (EER) in the range of 9% to 13% depending on the test set. This improves previously reported footstep recognition rates in the spatial domain up to 4% EER.

Original languageEnglish
Title of host publicationIEEE Sensors, SENSORS 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479982875
DOIs
Publication statusPublished - 5 Jan 2016
Externally publishedYes
Event15th IEEE Sensors Conference, SENSORS 2016 - Orlando, United States
Duration: 30 Oct 20162 Nov 2016

Publication series

NameProceedings of IEEE Sensors
Volume0
ISSN (Print)1930-0395
ISSN (Electronic)2168-9229

Conference

Conference15th IEEE Sensors Conference, SENSORS 2016
Country/TerritoryUnited States
CityOrlando
Period30/10/162/11/16

Keywords

  • convolutional neural networks
  • deep learning
  • floor sensor system
  • gait analysis
  • machine learning
  • pattern recognition

Fingerprint

Dive into the research topics of 'Spatial footstep recognition by convolutional neural networks for biometrie applications'. Together they form a unique fingerprint.

Cite this