Analysis of Spatio-temporal Representations for Robust Footstep Recognition with Deep Residual Neural NetworksCitation formats

Standard

Analysis of Spatio-temporal Representations for Robust Footstep Recognition with Deep Residual Neural Networks. / Costilla Reyes, Omar; Scully, Patricia; Ozanyan, Krikor.

In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 31.01.2018, p. 1-12.

Research output: Contribution to journalArticle

Harvard

Costilla Reyes, O, Scully, P & Ozanyan, K 2018, 'Analysis of Spatio-temporal Representations for Robust Footstep Recognition with Deep Residual Neural Networks' IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-12. https://doi.org/10.1109/TPAMI.2018.2799847

APA

Vancouver

Costilla Reyes O, Scully P, Ozanyan K. Analysis of Spatio-temporal Representations for Robust Footstep Recognition with Deep Residual Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018 Jan 31;1-12. https://doi.org/10.1109/TPAMI.2018.2799847

Author

Costilla Reyes, Omar ; Scully, Patricia ; Ozanyan, Krikor. / Analysis of Spatio-temporal Representations for Robust Footstep Recognition with Deep Residual Neural Networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018 ; pp. 1-12.

Bibtex

@article{e4322f7409ba42fcaa561209445925d2,
title = "Analysis of Spatio-temporal Representations for Robust Footstep Recognition with Deep Residual Neural Networks",
abstract = "Human footsteps can provide a unique behavioural pattern for robust biometric systems. We propose spatio-temporal footstep representations from floor-only sensor data in advanced computational models for automatic biometric verification. Our models deliver an artificial intelligence capable of effectively differentiating the fine-grained variability of footsteps between legitimate users (clients) and impostor users of the biometric system. The methodology is validated in the largest to date footstep database, containing nearly 20,000 footstep signals from more than 120 users. The database is organized by considering a large cohort of impostors and a small set of clients to verify the reliability of biometric systems. We provide experimental results in 3 critical data-driven security scenarios, according to the amount of footstep data made available for model training: at airports security checkpoints (smallest training set), workspace environments (medium training set) and home environments (largest training set). We report state-of-the-art footstep recognition rates with an optimal equal false acceptance and false rejection rate of 0.7{\%} (equal error rate), an improvement ratio of 371{\%} from previous state-of-the-art. We perform a feature analysis of deep residual neural networks showing effective clustering of clients footstep data and provide insights of the feature learning process.",
author = "{Costilla Reyes}, Omar and Patricia Scully and Krikor Ozanyan",
year = "2018",
month = "1",
day = "31",
doi = "10.1109/TPAMI.2018.2799847",
language = "English",
pages = "1--12",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "Institute of Electrical and Electronics Engineers",

}

RIS

TY - JOUR

T1 - Analysis of Spatio-temporal Representations for Robust Footstep Recognition with Deep Residual Neural Networks

AU - Costilla Reyes, Omar

AU - Scully, Patricia

AU - Ozanyan, Krikor

PY - 2018/1/31

Y1 - 2018/1/31

N2 - Human footsteps can provide a unique behavioural pattern for robust biometric systems. We propose spatio-temporal footstep representations from floor-only sensor data in advanced computational models for automatic biometric verification. Our models deliver an artificial intelligence capable of effectively differentiating the fine-grained variability of footsteps between legitimate users (clients) and impostor users of the biometric system. The methodology is validated in the largest to date footstep database, containing nearly 20,000 footstep signals from more than 120 users. The database is organized by considering a large cohort of impostors and a small set of clients to verify the reliability of biometric systems. We provide experimental results in 3 critical data-driven security scenarios, according to the amount of footstep data made available for model training: at airports security checkpoints (smallest training set), workspace environments (medium training set) and home environments (largest training set). We report state-of-the-art footstep recognition rates with an optimal equal false acceptance and false rejection rate of 0.7% (equal error rate), an improvement ratio of 371% from previous state-of-the-art. We perform a feature analysis of deep residual neural networks showing effective clustering of clients footstep data and provide insights of the feature learning process.

AB - Human footsteps can provide a unique behavioural pattern for robust biometric systems. We propose spatio-temporal footstep representations from floor-only sensor data in advanced computational models for automatic biometric verification. Our models deliver an artificial intelligence capable of effectively differentiating the fine-grained variability of footsteps between legitimate users (clients) and impostor users of the biometric system. The methodology is validated in the largest to date footstep database, containing nearly 20,000 footstep signals from more than 120 users. The database is organized by considering a large cohort of impostors and a small set of clients to verify the reliability of biometric systems. We provide experimental results in 3 critical data-driven security scenarios, according to the amount of footstep data made available for model training: at airports security checkpoints (smallest training set), workspace environments (medium training set) and home environments (largest training set). We report state-of-the-art footstep recognition rates with an optimal equal false acceptance and false rejection rate of 0.7% (equal error rate), an improvement ratio of 371% from previous state-of-the-art. We perform a feature analysis of deep residual neural networks showing effective clustering of clients footstep data and provide insights of the feature learning process.

U2 - 10.1109/TPAMI.2018.2799847

DO - 10.1109/TPAMI.2018.2799847

M3 - Article

SP - 1

EP - 12

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

ER -