Analysis of spatial domain information for footstep recognition

Vera-Rodríguez, Rubén; Mason, John S.; Fiérrez, Julián; Ortega‐Garcia, Javier

doi:10.1049/iet-cvi.2010.0189

Cited by 20 publications

(28 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In each case, except for [2], [17], the databases are divided into training and testing sets, but none use independent development and evaluation sets, with exception of our works [11], [20], [21], [22], a limitation which makes application performance predictions much more difficult. In the work that follows, an emphasis is placed on training/test and validation/evaluation sets.…”

Section: Related Workmentioning

confidence: 99%

“…Also, different people provided data during different periods of time and in different number of sessions, because as stated before, the objective was to obtain a large database. More details about the database can be found in [22].…”

Section: Database Collection and Labellingmentioning

confidence: 99%

“…The spatial domain information extracted here is a novel approach which considers the distribution of the accumulated pressure along a footstep signal in the spatial domain. In this case, the individual GRF (GRF i ) of each footstep sensor is integrated along the time axis, obtaining a single value of the accumulated pressure (AP i ) for each sensor of the array for a footstep signal, similar to the work in [22]. The accumulated pressure (AP i ) is the measure used to study the distribution of the pressure across the spatial domain of the signals, and it is defined by: It is worth noting that Equations 2 and 6 use the 88 profiles of GRF i to extract time and spatial information respectively.…”

Section: Spatial Domain Features (Bspace)mentioning

confidence: 99%

See 2 more Smart Citations

Comparative Analysis and Fusion of Spatiotemporal Information for Footstep Recognition

Vera-Rodríguez

Mason

Fiérrez

et al. 2013

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Esta es la versión de autor del artículo publicado en: This is an author produced version of a paper published in: Abstract-Footstep recognition is a relatively new biometric, which aims to discriminate persons using walking characteristics extracted from floor-based sensors. This paper reports for the first time a comparative assessment of the spatio-temporal information contained in the footstep signals for person recognition. Experiments are carried out on the largest footstep database collected to date, with almost 20,000 valid footstep signals and more than 120 persons. Results show very similar performance for both spatial and temporal approaches (5% to 15% EER depending on the experimental setup), and a significant improvement is achieved for their fusion (2.5% to 10% EER). The assessment protocol is focused on the influence of the quantity of data used in the reference models, which serves to simulate conditions of different potential applications such as smart homes or security access scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Database Collection and Labellingmentioning

confidence: 99%

Section: Spatial Domain Features (Bspace)mentioning

confidence: 99%

See 1 more Smart Citation

Comparative Analysis and Fusion of Spatiotemporal Information for Footstep Recognition

Vera-Rodríguez

Mason

Fiérrez

et al. 2013

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…Regarding the classifier, a support vector machine (SVM) [18] was adopted with a radial basis function (RBF) as the kernel, due to very good performance in previous studies in this area [2,19].…”

Section: Experimental Protocolmentioning

confidence: 99%

A novel approach of gait recognition through fusion with footstep information

Vera-Rodríguez

Fiérrez

Mason

et al. 2013

2013 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: AbstractThis paper is focused on two biometric modes which are very linked together: gait and footstep biometrics. Footstep recognition is a relatively new biometric based on signals extracted from floor sensors, while gait has been more researched and it is based on video sequences of people walking. This paper reports a directly comparative assessment of both biometrics using the same database (SFootBD) and experimental protocols. A fusion of the two modes leads to an enhanced gait recognition performance, as the information from both modes comes from different capturing devices and is not very correlated. This fusion could find application in indoor scenarios where a gait recognition system is present, such as in security access (e.g. security gate at airports) or smart homes. Gait and footstep systems achieve results of 8.4% and 10.7% EER respectively, which can be significantly improved to 4.8% EER with their fusion at the score level into a walking biometric.

show abstract

“…The existing footstep identification methods [5][6][7][8][9][10][11][12][13][14][15] utilized acoustic, psycho-acoustic parameters or footstep pressure dynamics captured from people walking over an instrumented sensing area as footstep features. They are sensitive to changes of footwear, floor and person's psychological state, and so in these methods, the footwear, floor and walking manner (single person in general psychological makeup) were limited.…”

Section: Introductionmentioning

confidence: 99%

Footstep-Identification System Based on Walking Interval

Wang

Yang

et al. 2015

IEEE Intell. Syst.

View full text Add to dashboard Cite

Footsteps, as a main kind of behavioral trait are a universally available signal, but it remains a challenging problem to construct an identity verification system based on them since footsteps not only reflect a person's physiological basis but also depend on the person's psychological makeup, footwear and floor. This paper describes a novel footstep identification system. In order to eliminate footwear and floor variations as limiting factors, the footstep duration and interval times are extracted from footsteps and a timing vector is obtained as the feature. In order to smooth instability of footsteps, we develop a novel pattern recognition method, in which the training procedure can be split into several parallel subprocedures, and each subprocedure only considers one class samples and involves several vector operations. So, it can be periodically retrained using the user's recent several successful identification footsteps. Then, diversification similarity degree is introduced and regarded as similarity measure, which is invariant to the change of examinee's psychological makeup between two footstep recording courses. Theoretical and experimental results show this system is relatively robust to the variations of footwear, floor, and the examinee's psychological makeup, and yields a better classification performance compared with the existing methods.

show abstract

Analysis of spatial domain information for footstep recognition

Abstract: Esta es la versión de autor del artículo publicado en: This is an author produced version of a paper published in:

Cited by 20 publications

References 12 publications

Comparative Analysis and Fusion of Spatiotemporal Information for Footstep Recognition

Comparative Analysis and Fusion of Spatiotemporal Information for Footstep Recognition

A novel approach of gait recognition through fusion with footstep information

Footstep-Identification System Based on Walking Interval

Contact Info

Product

Resources

About