INSTRUCTIONS FOR DOWNLOADING
Download license agreement,
send by email one signed and scanned copy to atvsuam.es according to the instructions given in point 2.
Send an email to atvsuam.es, as follows:
[DATABASE download: SFootBD]
Body: Your name, e-mail, telephone
number, organization, postal mail, purpose for which you will use
the database, time and date at which you sent the email with the
signed license agreement.
Once the email copy of the license
agreement has been received at ATVS, you will receive an email with a
username, a password, and a time slot to download the database.
Download the database, for which you will need to provide the
authentication information given in step 4. After you finish the
download, please notify by email to atvsuam.es that you have
successfully completed the transaction.
For more information, please contact: atvsuam.es
DESCRIPTION OF SFootBD
The database is comprised of 19,980 footstep signals (9,990 stride signals) from 127 users, as described in [PAMI2012] and [IET2011].
The footstep signals are stored in .mat (MATLAB) files. After loading each file, footstep signals corresponding to the right and left foot are stored respectively in two matrices (dataR and dataL) of dimensions 2200 by 88, i.e., 2200 time samples and 88 piezoelectric sensors.
The nomenclature followed to name the signature files is the date of collection, as follows: yyyy-mm-dd_hh-xx-ss_msc.mat
As described in [PAMI2012] and [IET2011], the database is divided into different datasets to carry out the experimental work: Training set, Impostors set, Validation test set and Evaluation test set.
There is an index file specifying the signals used in each dataset. Index files corresponding to the Benchmark baseline (40 clients and 40 signals per client) are included with this release of the database. These index files are stored in .txt files with two columns:
COLUMN 1: represents the user identifier [15, 16, ... , 120]
COLUMN 2: represents footstep file, e.g., 2007-05-22_15-15-21_971
For further information regarding the database, the different features approaches extracted from the data and the experimental work we refer the reader to (all these articles are publicly available in the publications section of the ATVS group webpage.)
[PAMI2012] R. Vera-Rodriguez, J. Mason, J. Fierrez and J. Ortega-Garcia,
"Comparative Analysis and Fusion of Spatio-Temporal Information for Footstep Recognition",
in IEEE Pattern Analysis and Machine Intelligence, 2012 (DOI: 10.1109/TPAMI.2012.164).
[IET2011] R. Vera-Rodriguez, J. Mason, J. Fierrez and J. Ortega-Garcia,
"Analysis of Spatial Domain Information for Footstep Recognition",
IET Computer Vision, 5, 380-388, 2011 (DOI: 10.1049/iet-cvi.2010.0189).
Please remember to reference articles [PAMI2012] and [IET2011] on any work made public, whatever the form, based directly or indirectly on any part of the SFootBD.