Deep Learning-based identification of human gait by radar micro-Doppler measurements

V. S. Papanastasiou; R. P. Trommel; R. I.A. Harmanny; A. Yarovoy

doi:10.1109/EuRAD48048.2021.00024

Deep Learning-based identification of human gait by radar micro-Doppler measurements

V. S. Papanastasiou, R. P. Trommel, R. I.A. Harmanny, A. Yarovoy

Microwave Sensing, Signals & Systems

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

15 Citations (Scopus)

11 Downloads (Pure)

Abstract

For the first time identification of human individuals using micro-Doppler (m-D) features measured at X-band has been demonstrated. Deep Convolutional Neural Networks (DCNNs) have been used to perform classification. Inspection and visualization of the classification results were performed using Uniform Manifold Approximation and Projection (UMAP). Classification accuracy of above 93.5% is obtained for a population of 22 subjects. The results show that human identification on a specific population based on X-band m-D measurements can be performed reliably using a DCNN.

Original language	English
Title of host publication	EuRAD 2020 - 2020 17th European Radar Conference
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	49-52
Number of pages	4
ISBN (Electronic)	9782874870613
DOIs	https://doi.org/10.1109/EuRAD48048.2021.00024
Publication status	Published - 2021
Event	17th European Radar Conference, EuRAD 2020 - Utrecht, Netherlands Duration: 13 Jan 2021 → 15 Jan 2021

Publication series

Name	EuRAD 2020 - 2020 17th European Radar Conference

Conference

Conference	17th European Radar Conference, EuRAD 2020
Country/Territory	Netherlands
City	Utrecht
Period	13/01/21 → 15/01/21

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

classification
deep learning
identification
micro-Doppler
radar

Access to Document

10.1109/EuRAD48048.2021.00024

09337435Final published version, 1.91 MB

Cite this

Papanastasiou, V. S., Trommel, R. P., Harmanny, R. I. A., & Yarovoy, A. (2021). Deep Learning-based identification of human gait by radar micro-Doppler measurements. In EuRAD 2020 - 2020 17th European Radar Conference (pp. 49-52). Article 9337435 (EuRAD 2020 - 2020 17th European Radar Conference). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/EuRAD48048.2021.00024

@inproceedings{c88c188ed01a47b29abd04349cfc0da5,

title = "Deep Learning-based identification of human gait by radar micro-Doppler measurements",

abstract = "For the first time identification of human individuals using micro-Doppler (m-D) features measured at X-band has been demonstrated. Deep Convolutional Neural Networks (DCNNs) have been used to perform classification. Inspection and visualization of the classification results were performed using Uniform Manifold Approximation and Projection (UMAP). Classification accuracy of above 93.5% is obtained for a population of 22 subjects. The results show that human identification on a specific population based on X-band m-D measurements can be performed reliably using a DCNN. ",

keywords = "classification, deep learning, identification, micro-Doppler, radar",

author = "Papanastasiou, {V. S.} and Trommel, {R. P.} and Harmanny, {R. I.A.} and A. Yarovoy",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 17th European Radar Conference, EuRAD 2020 ; Conference date: 13-01-2021 Through 15-01-2021",

year = "2021",

doi = "10.1109/EuRAD48048.2021.00024",

language = "English",

series = "EuRAD 2020 - 2020 17th European Radar Conference",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "49--52",

booktitle = "EuRAD 2020 - 2020 17th European Radar Conference",

address = "United States",

}

Papanastasiou, VS, Trommel, RP, Harmanny, RIA & Yarovoy, A 2021, Deep Learning-based identification of human gait by radar micro-Doppler measurements. in EuRAD 2020 - 2020 17th European Radar Conference., 9337435, EuRAD 2020 - 2020 17th European Radar Conference, Institute of Electrical and Electronics Engineers (IEEE), pp. 49-52, 17th European Radar Conference, EuRAD 2020, Utrecht, Netherlands, 13/01/21. https://doi.org/10.1109/EuRAD48048.2021.00024

Deep Learning-based identification of human gait by radar micro-Doppler measurements. / Papanastasiou, V. S.; Trommel, R. P.; Harmanny, R. I.A. et al.
EuRAD 2020 - 2020 17th European Radar Conference. Institute of Electrical and Electronics Engineers (IEEE), 2021. p. 49-52 9337435 (EuRAD 2020 - 2020 17th European Radar Conference).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Deep Learning-based identification of human gait by radar micro-Doppler measurements

AU - Papanastasiou, V. S.

AU - Trommel, R. P.

AU - Harmanny, R. I.A.

AU - Yarovoy, A.

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2021

Y1 - 2021

N2 - For the first time identification of human individuals using micro-Doppler (m-D) features measured at X-band has been demonstrated. Deep Convolutional Neural Networks (DCNNs) have been used to perform classification. Inspection and visualization of the classification results were performed using Uniform Manifold Approximation and Projection (UMAP). Classification accuracy of above 93.5% is obtained for a population of 22 subjects. The results show that human identification on a specific population based on X-band m-D measurements can be performed reliably using a DCNN.

AB - For the first time identification of human individuals using micro-Doppler (m-D) features measured at X-band has been demonstrated. Deep Convolutional Neural Networks (DCNNs) have been used to perform classification. Inspection and visualization of the classification results were performed using Uniform Manifold Approximation and Projection (UMAP). Classification accuracy of above 93.5% is obtained for a population of 22 subjects. The results show that human identification on a specific population based on X-band m-D measurements can be performed reliably using a DCNN.

KW - classification

KW - deep learning

KW - identification

KW - micro-Doppler

KW - radar

UR - http://www.scopus.com/inward/record.url?scp=85100875203&partnerID=8YFLogxK

U2 - 10.1109/EuRAD48048.2021.00024

DO - 10.1109/EuRAD48048.2021.00024

M3 - Conference contribution

AN - SCOPUS:85100875203

T3 - EuRAD 2020 - 2020 17th European Radar Conference

SP - 49

EP - 52

BT - EuRAD 2020 - 2020 17th European Radar Conference

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 17th European Radar Conference, EuRAD 2020

Y2 - 13 January 2021 through 15 January 2021

ER -

Deep Learning-based identification of human gait by radar micro-Doppler measurements

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this