The Infrared Image Based Non-Contact Monitoring of Respiratory Waveform Through Deep Kalman Filter

Respiratory waveform is one of the most important physiological signals containing essential pathophysiological information. The classical monitoring of respiratory waveform is based on the flow meter with contacted inputs. A non-contact respiratory waveform monitoring method is needed to bring a be...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Medical Measurement and Applications (MEMEA), IEEE International Workshop on s. 1 - 6
Hlavní autori: Sun, Hao, Huang, Zhipei, Tong, Yonggang, Shan, Guangcun, Dai, Xuewu, Qin, Fei
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 26.06.2024
Predmet:
ISSN:2837-5882
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Respiratory waveform is one of the most important physiological signals containing essential pathophysiological information. The classical monitoring of respiratory waveform is based on the flow meter with contacted inputs. A non-contact respiratory waveform monitoring method is needed to bring a better patient experience, allow more application scenarios and provide additional measurements to gain an in-depth understanding of the respiration system. In this paper, we proposed a novel infrared image-based non-contact monitoring method which successfully obtains the detailed preserved respiratory waveform for the first time. The obtained infrared image is modelled as temperature distribution over a spatial field instead of a simple grey image, which is decided mainly by the flow speed. And an efficient analytical model guided mapping function from raw high-dimensional observations into temporal flow sequences is developed to replace the simple average over the region of interests. As a result, the manual-involved measurement noises can be significantly suppressed. To further mitigate the residual noises, a deep Kalman filter is designed to make use of the self-evolution model of the respiration system. The experimental results have validated the accuracy of the proposed method.
AbstractList Respiratory waveform is one of the most important physiological signals containing essential pathophysiological information. The classical monitoring of respiratory waveform is based on the flow meter with contacted inputs. A non-contact respiratory waveform monitoring method is needed to bring a better patient experience, allow more application scenarios and provide additional measurements to gain an in-depth understanding of the respiration system. In this paper, we proposed a novel infrared image-based non-contact monitoring method which successfully obtains the detailed preserved respiratory waveform for the first time. The obtained infrared image is modelled as temperature distribution over a spatial field instead of a simple grey image, which is decided mainly by the flow speed. And an efficient analytical model guided mapping function from raw high-dimensional observations into temporal flow sequences is developed to replace the simple average over the region of interests. As a result, the manual-involved measurement noises can be significantly suppressed. To further mitigate the residual noises, a deep Kalman filter is designed to make use of the self-evolution model of the respiration system. The experimental results have validated the accuracy of the proposed method.
Author Dai, Xuewu
Huang, Zhipei
Tong, Yonggang
Shan, Guangcun
Sun, Hao
Qin, Fei
Author_xml – sequence: 1
  givenname: Hao
  surname: Sun
  fullname: Sun, Hao
  email: sunhao21@mails.ucas.ac.cn
  organization: School of EECE, Univ. of Chinese Academy of Sciences,Beijing,China
– sequence: 2
  givenname: Zhipei
  surname: Huang
  fullname: Huang, Zhipei
  email: zhphuang@ucas.ac.cn
  organization: School of EECE, Univ. of Chinese Academy of Sciences,Beijing,China
– sequence: 3
  givenname: Yonggang
  surname: Tong
  fullname: Tong, Yonggang
  email: tongyonggang20@mails.ucas.ac.cn
  organization: School of EECE, Univ. of Chinese Academy of Sciences,Beijing,China
– sequence: 4
  givenname: Guangcun
  surname: Shan
  fullname: Shan, Guangcun
  email: gcshan@buaa.edu.cn
  organization: School of IOE, Beihang University,Beijing,China
– sequence: 5
  givenname: Xuewu
  surname: Dai
  fullname: Dai, Xuewu
  email: xuewu.dai@northumbria.ac.uk
  organization: Northumbria University,Department of MPEE,Newcastle-upon-Tyne,UK
– sequence: 6
  givenname: Fei
  surname: Qin
  fullname: Qin, Fei
  email: fqin1982@ucas.ac.cn
  organization: School of EECE, Univ. of Chinese Academy of Sciences,Beijing,China
BookMark eNo1kNtKAzEYhKMoqLVv4EVeYGsOuzlc1mq12CpIxcvyZ_dPG-kmJbsKfXsX1KsZ5oNhmCtyFlNEQihnE86ZvV3hCqeKKSUngolywllllbHlCRlbbY2smGTaWnlKLoWRuqiMERdk3HWfjA2IM2bUJXHrHdJF9BkyNnTRwhbpHXSDf0mxmKXYQ93TVYqhTznELU2evmF3CBmG4Eg_4Bt9yi1d73L62u7oPeKBPsO-hUjnYd9jvibnHvYdjv90RN7nD-vZU7F8fVzMpssicK36grthbcO0Uh6N1uAsZ85LXwvQqnSN5U2NZQ2VU16q2gloBGpsQDghvdByRG5-ewMibg45tJCPm_9b5A82tFrJ
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/MeMeA60663.2024.10596894
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350307993
EISSN 2837-5882
EndPage 6
ExternalDocumentID 10596894
Genre orig-research
GrantInformation_xml – fundername: Fundamental Research Funds for Central Universities
  funderid: 10.13039/501100012476
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i176t-1b799d0766fe877ab910bf3fc2a764bd91dce4ca5b6f36cb2ad2e7eda2b23f273
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001292762200167&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:36:36 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i176t-1b799d0766fe877ab910bf3fc2a764bd91dce4ca5b6f36cb2ad2e7eda2b23f273
PageCount 6
ParticipantIDs ieee_primary_10596894
PublicationCentury 2000
PublicationDate 2024-June-26
PublicationDateYYYYMMDD 2024-06-26
PublicationDate_xml – month: 06
  year: 2024
  text: 2024-June-26
  day: 26
PublicationDecade 2020
PublicationTitle Medical Measurement and Applications (MEMEA), IEEE International Workshop on
PublicationTitleAbbrev MEMEA
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003010086
Score 1.8746142
Snippet Respiratory waveform is one of the most important physiological signals containing essential pathophysiological information. The classical monitoring of...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Detail-preserving
Flowmeters
Gain measurement
Kalman filter
Kalman filters
Manuals
Noise
Non-contact
Respiratory waveform
Temperature distribution
Temperature measurement
Thermography
Title The Infrared Image Based Non-Contact Monitoring of Respiratory Waveform Through Deep Kalman Filter
URI https://ieeexplore.ieee.org/document/10596894
WOSCitedRecordID wos001292762200167&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6EeNCLL4zvzMHrwm67tPToi0gMhBiM3Egf04REdgku_H7bXRA9ePDWNGnTzLSdb96E3Drrb4X0Sg5XVkepZjSSTsaRQeOEUdImzJTNJsRg0BmP5XCdrF7mwiBiGXyGzTAsffk2N8tgKmsFLMA7Mq2RmhC8Stb6Nqj4mxrw-SZaJ5atPvbxLgB05vVAmjY3y381UinlSPfgnyc4JI1tRh4Mv2XNEdnB7Jjs_ygmeEK05zj0MrcIIeXQm_mPAu69jLIwyLMoVKFSpoDqDYcVkDt43Tra4V2tMCBYGFWte-ARcQ4v6mOmMuhOg1e9Qd66T6OH52jdQSGaJoIXUaKFlDYWnDvsCKG0BwfaMWeoEjzVVibWYGpUW3PHuNFUWYoCraKaMueRzSmpZ3mGZwQ8sMFYUo7IeCpZotrMU4f5LVXC_N7npBHINZlXRTImG0pd_DF_SfYCU0LUFeVXpF4slnhNds2qmH4ubkrWfgGsVKZi
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JbsIwELVaWqntpRtV9_rQayCxg42P3RAIiFBFVW7Iy1hCggTRwPfXDlt76KG3KFJG0czY8-xZHkKP1jivEO6Qw6RRQawoCYQVYaBBW66lMBHVBdkET5L6YCB6q2b1ohcGAIriM6j4xyKXbzI991dlVY8FWF3Eu2jPU2et2rU2VyrOVz1CX9frhKLahS48eYhO3UmQxJW1gF9UKkUkaRz_8x9OUHnbk4d7m2hzinYgPUNHP8YJniPlbI5bqZ35onLcmritAj-7KGVwkqWBn0MldY6Xq9h_gTOL37epdvwpF-AxLO4vyXvwK8AUt-V4IlPcGPm8ehl9NN76L81gxaEQjCLO8iBSXAgTcsYs1DmXysEDZanVRHIWKyMioyHWsqaYpUwrIg0BDkYSRah12OYCldIshUuEHbSBUBAGQFksaCRr1GmHOpEyok72FSp7dQ2nyzEZw7Wmrv94_4AOmv1uZ9hpJe0bdOgN5GuwCLtFpXw2hzu0rxf56Gt2X5j5G4Vbqas
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Medical+Measurement+and+Applications+%28MEMEA%29%2C+IEEE+International+Workshop+on&rft.atitle=The+Infrared+Image+Based+Non-Contact+Monitoring+of+Respiratory+Waveform+Through+Deep+Kalman+Filter&rft.au=Sun%2C+Hao&rft.au=Huang%2C+Zhipei&rft.au=Tong%2C+Yonggang&rft.au=Shan%2C+Guangcun&rft.date=2024-06-26&rft.pub=IEEE&rft.eissn=2837-5882&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FMeMeA60663.2024.10596894&rft.externalDocID=10596894