KinRes

Depth sensor noise reduction in contactless respiratory monitoring

Kaveh Bakhtiyari, Jörgen Ziegler, Hafizah Husain

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a novel reliable solution, named KinRes, to extract contactless respiratory signal via an IR-3D Depth sensor (Microsoft Kinect 2) on human subjects interacting with a computer. The depth sensor is very sensitive to the minor changes so that the body movements impose noise in the depth values. Previous studies on contactless respiratory concentrated solely on the still laid subjects on a surface to minimize the possible artifacts. To overcome these limitations, we low-pass filter the extracted signal. Then, a greedy selfcorrection algorithm is developed to correct the false detected peaks & troughs. The processed signal is validated with a simultaneous signal from a respiratory belt. This framework improved the accuracy of the signal by 24% for the subjects in a normal sitting position.

Original languageEnglish
Title of host publicationProceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017
PublisherAssociation for Computing Machinery
Pages472-475
Number of pages4
VolumePart F132400
ISBN (Electronic)9781450363631
DOIs
Publication statusPublished - 23 May 2017
Event11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017 - Barcelona, Spain
Duration: 23 May 201726 May 2017

Other

Other11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017
CountrySpain
CityBarcelona
Period23/5/1726/5/17

Fingerprint

Noise abatement
Monitoring
Sensors
Low pass filters

Keywords

  • Greedy Algorithm
  • Microsoft Kinect
  • Signal Processing

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Bakhtiyari, K., Ziegler, J., & Husain, H. (2017). KinRes: Depth sensor noise reduction in contactless respiratory monitoring. In Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017 (Vol. Part F132400, pp. 472-475). Association for Computing Machinery. https://doi.org/10.1145/3154862.3154896

KinRes : Depth sensor noise reduction in contactless respiratory monitoring. / Bakhtiyari, Kaveh; Ziegler, Jörgen; Husain, Hafizah.

Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017. Vol. Part F132400 Association for Computing Machinery, 2017. p. 472-475.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bakhtiyari, K, Ziegler, J & Husain, H 2017, KinRes: Depth sensor noise reduction in contactless respiratory monitoring. in Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017. vol. Part F132400, Association for Computing Machinery, pp. 472-475, 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017, Barcelona, Spain, 23/5/17. https://doi.org/10.1145/3154862.3154896
Bakhtiyari K, Ziegler J, Husain H. KinRes: Depth sensor noise reduction in contactless respiratory monitoring. In Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017. Vol. Part F132400. Association for Computing Machinery. 2017. p. 472-475 https://doi.org/10.1145/3154862.3154896
Bakhtiyari, Kaveh ; Ziegler, Jörgen ; Husain, Hafizah. / KinRes : Depth sensor noise reduction in contactless respiratory monitoring. Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017. Vol. Part F132400 Association for Computing Machinery, 2017. pp. 472-475
@inproceedings{9d99160f7fc24c76afa47a3383e7eef5,
title = "KinRes: Depth sensor noise reduction in contactless respiratory monitoring",
abstract = "This paper proposes a novel reliable solution, named KinRes, to extract contactless respiratory signal via an IR-3D Depth sensor (Microsoft Kinect 2) on human subjects interacting with a computer. The depth sensor is very sensitive to the minor changes so that the body movements impose noise in the depth values. Previous studies on contactless respiratory concentrated solely on the still laid subjects on a surface to minimize the possible artifacts. To overcome these limitations, we low-pass filter the extracted signal. Then, a greedy selfcorrection algorithm is developed to correct the false detected peaks & troughs. The processed signal is validated with a simultaneous signal from a respiratory belt. This framework improved the accuracy of the signal by 24{\%} for the subjects in a normal sitting position.",
keywords = "Greedy Algorithm, Microsoft Kinect, Signal Processing",
author = "Kaveh Bakhtiyari and J{\"o}rgen Ziegler and Hafizah Husain",
year = "2017",
month = "5",
day = "23",
doi = "10.1145/3154862.3154896",
language = "English",
volume = "Part F132400",
pages = "472--475",
booktitle = "Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - KinRes

T2 - Depth sensor noise reduction in contactless respiratory monitoring

AU - Bakhtiyari, Kaveh

AU - Ziegler, Jörgen

AU - Husain, Hafizah

PY - 2017/5/23

Y1 - 2017/5/23

N2 - This paper proposes a novel reliable solution, named KinRes, to extract contactless respiratory signal via an IR-3D Depth sensor (Microsoft Kinect 2) on human subjects interacting with a computer. The depth sensor is very sensitive to the minor changes so that the body movements impose noise in the depth values. Previous studies on contactless respiratory concentrated solely on the still laid subjects on a surface to minimize the possible artifacts. To overcome these limitations, we low-pass filter the extracted signal. Then, a greedy selfcorrection algorithm is developed to correct the false detected peaks & troughs. The processed signal is validated with a simultaneous signal from a respiratory belt. This framework improved the accuracy of the signal by 24% for the subjects in a normal sitting position.

AB - This paper proposes a novel reliable solution, named KinRes, to extract contactless respiratory signal via an IR-3D Depth sensor (Microsoft Kinect 2) on human subjects interacting with a computer. The depth sensor is very sensitive to the minor changes so that the body movements impose noise in the depth values. Previous studies on contactless respiratory concentrated solely on the still laid subjects on a surface to minimize the possible artifacts. To overcome these limitations, we low-pass filter the extracted signal. Then, a greedy selfcorrection algorithm is developed to correct the false detected peaks & troughs. The processed signal is validated with a simultaneous signal from a respiratory belt. This framework improved the accuracy of the signal by 24% for the subjects in a normal sitting position.

KW - Greedy Algorithm

KW - Microsoft Kinect

KW - Signal Processing

UR - http://www.scopus.com/inward/record.url?scp=85041181026&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041181026&partnerID=8YFLogxK

U2 - 10.1145/3154862.3154896

DO - 10.1145/3154862.3154896

M3 - Conference contribution

VL - Part F132400

SP - 472

EP - 475

BT - Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare, PervasiveHealth 2017

PB - Association for Computing Machinery

ER -