Continuous human activity recognition for arbitrary directions with distributed radars

Ronny Gerhard Guendel; Matteo Unterhorst; Ennio Gambi; Francesco Fioranelli; Alexander Yarovoy

doi:10.1109/RadarConf2147009.2021.9454972

Continuous human activity recognition for arbitrary directions with distributed radars

Ronny Gerhard Guendel, Matteo Unterhorst, Ennio Gambi, Francesco Fioranelli, Alexander Yarovoy

Microwave Sensing, Signals & Systems

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

12 Citations (Scopus)

14 Downloads (Pure)

Abstract

Continuous Activities of Daily Living (ADL) recognition in an arbitrary movement direction using five distributed pulsed Ultra-Wideband (UWB) radars in a coordinated network is proposed. Classification approaches in unconstrained activity trajectories that render a more natural occurrence for Human Activity Recognition (HAR) are investigated. Feature and decision fusion methods are applied to the priorly extracted handcrafted features from the range-Doppler. A following multi-nomial logistic regression classifier, commonly known as Softmax, provides explicit probabilities associated with each target label. The outputs of these classifiers from different radar nodes were combined with a probability prediction balancing approach over time to improve performances. The final results show average improvements between 6.8% and 17.5% compared to the usage of any single radar in unconstrained directions

Original language	English
Title of host publication	2021 IEEE Radar Conference
Subtitle of host publication	Radar on the Move, RadarConf 2021
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	978-1-7281-7609-3
ISBN (Print)	978-1-7281-7610-9
DOIs	https://doi.org/10.1109/RadarConf2147009.2021.9454972
Publication status	Published - 2021
Event	2021 IEEE Radar Conference (RadarConf21): Radar on the Move - Atlanta, United States Duration: 7 May 2021 → 14 May 2021

Publication series

Name	IEEE National Radar Conference - Proceedings
Volume	2021-May
ISSN (Print)	1097-5659

Conference

Conference	2021 IEEE Radar Conference (RadarConf21)
Country/Territory	United States
City	Atlanta
Period	7/05/21 → 14/05/21

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

Micro-Doppler Classification
Distributed Radar
Assisted Living
Human Activity Recognition
Machine Learning

Access to Document

10.1109/RadarConf2147009.2021.9454972

09454972Final published version, 6.38 MB

Cite this

@inproceedings{e0252aea6fd6407ba7a6d627940886f2,

title = "Continuous human activity recognition for arbitrary directions with distributed radars",

abstract = "Continuous Activities of Daily Living (ADL) recognition in an arbitrary movement direction using five distributed pulsed Ultra-Wideband (UWB) radars in a coordinated network is proposed. Classification approaches in unconstrained activity trajectories that render a more natural occurrence for Human Activity Recognition (HAR) are investigated. Feature and decision fusion methods are applied to the priorly extracted handcrafted features from the range-Doppler. A following multi-nomial logistic regression classifier, commonly known as Softmax, provides explicit probabilities associated with each target label. The outputs of these classifiers from different radar nodes were combined with a probability prediction balancing approach over time to improve performances. The final results show average improvements between 6.8% and 17.5% compared to the usage of any single radar in unconstrained directions",

keywords = "Micro-Doppler Classification, Distributed Radar, Assisted Living, Human Activity Recognition, Machine Learning",

author = "Guendel, {Ronny Gerhard} and Matteo Unterhorst and Ennio Gambi and Francesco Fioranelli and Alexander 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.; 2021 IEEE Radar Conference (RadarConf21) : Radar on the Move ; Conference date: 07-05-2021 Through 14-05-2021",

year = "2021",

doi = "10.1109/RadarConf2147009.2021.9454972",

language = "English",

isbn = "978-1-7281-7610-9",

series = "IEEE National Radar Conference - Proceedings",

publisher = "IEEE ",

booktitle = "2021 IEEE Radar Conference",

address = "United States",

}

Guendel, RG, Unterhorst, M, Gambi, E, Fioranelli, F & Yarovoy, A 2021, Continuous human activity recognition for arbitrary directions with distributed radars. in 2021 IEEE Radar Conference: Radar on the Move, RadarConf 2021., 9454972, IEEE National Radar Conference - Proceedings, vol. 2021-May, IEEE , 2021 IEEE Radar Conference (RadarConf21), Atlanta, United States, 7/05/21. https://doi.org/10.1109/RadarConf2147009.2021.9454972

Continuous human activity recognition for arbitrary directions with distributed radars. / Guendel, Ronny Gerhard; Unterhorst, Matteo; Gambi, Ennio; Fioranelli, Francesco ; Yarovoy, Alexander.

2021 IEEE Radar Conference: Radar on the Move, RadarConf 2021. IEEE , 2021. 9454972 (IEEE National Radar Conference - Proceedings; Vol. 2021-May).

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

TY - GEN

T1 - Continuous human activity recognition for arbitrary directions with distributed radars

AU - Guendel, Ronny Gerhard

AU - Unterhorst, Matteo

AU - Gambi, Ennio

AU - Fioranelli, Francesco

AU - Yarovoy, Alexander

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 - Continuous Activities of Daily Living (ADL) recognition in an arbitrary movement direction using five distributed pulsed Ultra-Wideband (UWB) radars in a coordinated network is proposed. Classification approaches in unconstrained activity trajectories that render a more natural occurrence for Human Activity Recognition (HAR) are investigated. Feature and decision fusion methods are applied to the priorly extracted handcrafted features from the range-Doppler. A following multi-nomial logistic regression classifier, commonly known as Softmax, provides explicit probabilities associated with each target label. The outputs of these classifiers from different radar nodes were combined with a probability prediction balancing approach over time to improve performances. The final results show average improvements between 6.8% and 17.5% compared to the usage of any single radar in unconstrained directions

AB - Continuous Activities of Daily Living (ADL) recognition in an arbitrary movement direction using five distributed pulsed Ultra-Wideband (UWB) radars in a coordinated network is proposed. Classification approaches in unconstrained activity trajectories that render a more natural occurrence for Human Activity Recognition (HAR) are investigated. Feature and decision fusion methods are applied to the priorly extracted handcrafted features from the range-Doppler. A following multi-nomial logistic regression classifier, commonly known as Softmax, provides explicit probabilities associated with each target label. The outputs of these classifiers from different radar nodes were combined with a probability prediction balancing approach over time to improve performances. The final results show average improvements between 6.8% and 17.5% compared to the usage of any single radar in unconstrained directions

KW - Micro-Doppler Classification

KW - Distributed Radar

KW - Assisted Living

KW - Human Activity Recognition

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85112448900&partnerID=8YFLogxK

U2 - 10.1109/RadarConf2147009.2021.9454972

DO - 10.1109/RadarConf2147009.2021.9454972

M3 - Conference contribution

SN - 978-1-7281-7610-9

T3 - IEEE National Radar Conference - Proceedings

BT - 2021 IEEE Radar Conference

PB - IEEE

T2 - 2021 IEEE Radar Conference (RadarConf21)

Y2 - 7 May 2021 through 14 May 2021

ER -

Continuous human activity recognition for arbitrary directions with distributed radars

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Dataset of continuous human activities performed in arbitrary directions collected with a distributed radar network of five nodes

Cite this

Continuous human activity recognition for arbitrary directions with distributed radars

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Datasets

Dataset of continuous human activities performed in arbitrary directions collected with a distributed radar network of five nodes

Cite this