Derivative Target Line (DTL) for Continuous Human Activity Detection and Recognition

Ronny G. Guendel; Francesco Fioranelli; Alexander Yarovoy

doi:10.1109/RadarConf2043947.2020.9266383

Derivative Target Line (DTL) for Continuous Human Activity Detection and Recognition

Ronny G. Guendel, Francesco Fioranelli, Alexander Yarovoy

Microwave Sensing, Signals & Systems

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

3 Citations (Scopus)

24 Downloads (Pure)

Abstract

In this paper, we investigate the classification of Activities of Daily Living (ADL) by using a pulsed ultra-wideband radar. Specifically, we focus on contiguous activities that can be inseparable in time and share a common transition, such as walking and falling. The range-time data domain is deliberately exploited to determine transitions from translation activities to in-place activities and vice versa, using a simple, yet effective approach based on the proposed Derivative Target Line (DTL). The separation of different in-place activities is then addressed using an energy detector finding the onset and offset times. Furthermore, the possible ADL for classification are limited at any decision stage based on kinematic constraints of human movements. We show that such limitation of classes at any given time leads to a classification improvement over a classifier containing always all ADL classes.

Original language	English
Title of host publication	2020 IEEE Radar Conference, RadarConf 2020
Place of Publication	Piscataway
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Electronic)	978-1-7281-8942-0
ISBN (Print)	978-1-7281-8943-7
DOIs	https://doi.org/10.1109/RadarConf2043947.2020.9266383
Publication status	Published - 2020
Event	2020 IEEE Radar Conference (RadarConf20) - Florence, Italy Duration: 21 Sept 2020 → 25 Sept 2020

Publication series

Name	IEEE National Radar Conference - Proceedings
Volume	2020-September
ISSN (Print)	1097-5659

Conference

Conference	2020 IEEE Radar Conference (RadarConf20)
Country/Territory	Italy
City	Florence
Period	21/09/20 → 25/09/20

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

activities of daily living
assisted living
classification
feature fusion
machine learning
micro-Doppler
range-map

Access to Document

10.1109/RadarConf2043947.2020.9266383

09266383Final published version, 2.3 MB

Cite this

@inproceedings{adcb5e677a0948409c71b8e8c3d0de1d,

title = "Derivative Target Line (DTL) for Continuous Human Activity Detection and Recognition",

abstract = "In this paper, we investigate the classification of Activities of Daily Living (ADL) by using a pulsed ultra-wideband radar. Specifically, we focus on contiguous activities that can be inseparable in time and share a common transition, such as walking and falling. The range-time data domain is deliberately exploited to determine transitions from translation activities to in-place activities and vice versa, using a simple, yet effective approach based on the proposed Derivative Target Line (DTL). The separation of different in-place activities is then addressed using an energy detector finding the onset and offset times. Furthermore, the possible ADL for classification are limited at any decision stage based on kinematic constraints of human movements. We show that such limitation of classes at any given time leads to a classification improvement over a classifier containing always all ADL classes.",

keywords = "activities of daily living, assisted living, classification, feature fusion, machine learning, micro-Doppler, range-map",

author = "Guendel, {Ronny G.} 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.; 2020 IEEE Radar Conference (RadarConf20) ; Conference date: 21-09-2020 Through 25-09-2020",

year = "2020",

doi = "10.1109/RadarConf2043947.2020.9266383",

language = "English",

isbn = "978-1-7281-8943-7",

series = "IEEE National Radar Conference - Proceedings",

publisher = "IEEE",

pages = "1--6",

booktitle = "2020 IEEE Radar Conference, RadarConf 2020",

address = "United States",

}

Guendel, RG , Fioranelli, F & Yarovoy, A 2020, Derivative Target Line (DTL) for Continuous Human Activity Detection and Recognition. in 2020 IEEE Radar Conference, RadarConf 2020., 9266383, IEEE National Radar Conference - Proceedings, vol. 2020-September, IEEE, Piscataway, pp. 1-6, 2020 IEEE Radar Conference (RadarConf20), Florence, Italy, 21/09/20. https://doi.org/10.1109/RadarConf2043947.2020.9266383

Derivative Target Line (DTL) for Continuous Human Activity Detection and Recognition. / Guendel, Ronny G.; Fioranelli, Francesco ; Yarovoy, Alexander.
2020 IEEE Radar Conference, RadarConf 2020. Piscataway: IEEE, 2020. p. 1-6 9266383 (IEEE National Radar Conference - Proceedings; Vol. 2020-September).

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

TY - GEN

T1 - Derivative Target Line (DTL) for Continuous Human Activity Detection and Recognition

AU - Guendel, Ronny G.

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 - 2020

Y1 - 2020

N2 - In this paper, we investigate the classification of Activities of Daily Living (ADL) by using a pulsed ultra-wideband radar. Specifically, we focus on contiguous activities that can be inseparable in time and share a common transition, such as walking and falling. The range-time data domain is deliberately exploited to determine transitions from translation activities to in-place activities and vice versa, using a simple, yet effective approach based on the proposed Derivative Target Line (DTL). The separation of different in-place activities is then addressed using an energy detector finding the onset and offset times. Furthermore, the possible ADL for classification are limited at any decision stage based on kinematic constraints of human movements. We show that such limitation of classes at any given time leads to a classification improvement over a classifier containing always all ADL classes.

AB - In this paper, we investigate the classification of Activities of Daily Living (ADL) by using a pulsed ultra-wideband radar. Specifically, we focus on contiguous activities that can be inseparable in time and share a common transition, such as walking and falling. The range-time data domain is deliberately exploited to determine transitions from translation activities to in-place activities and vice versa, using a simple, yet effective approach based on the proposed Derivative Target Line (DTL). The separation of different in-place activities is then addressed using an energy detector finding the onset and offset times. Furthermore, the possible ADL for classification are limited at any decision stage based on kinematic constraints of human movements. We show that such limitation of classes at any given time leads to a classification improvement over a classifier containing always all ADL classes.

KW - activities of daily living

KW - assisted living

KW - classification

KW - feature fusion

KW - machine learning

KW - micro-Doppler

KW - range-map

UR - http://www.scopus.com/inward/record.url?scp=85098588315&partnerID=8YFLogxK

U2 - 10.1109/RadarConf2043947.2020.9266383

DO - 10.1109/RadarConf2043947.2020.9266383

M3 - Conference contribution

SN - 978-1-7281-8943-7

T3 - IEEE National Radar Conference - Proceedings

SP - 1

EP - 6

BT - 2020 IEEE Radar Conference, RadarConf 2020

PB - IEEE

CY - Piscataway

T2 - 2020 IEEE Radar Conference (RadarConf20)

Y2 - 21 September 2020 through 25 September 2020

ER -

Derivative Target Line (DTL) for Continuous Human Activity Detection and Recognition

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this