Deep Learning for Accurate Indoor Human Tracking with a mm-Wave Radar

We address the use of backscattered mm-wave radio signals to track humans as they move within indoor environments. The common approach in the literature leverages the extended Kalman filter (EKF) method, which however undergoes a severe performance degradation when the system evolution model is high...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the IEEE National Radar Conference (1996) s. 1 - 6
Hlavní autoři: Pegoraro, Jacopo, Solimini, Domenico, Matteo, Federico, Bashirov, Enver, Meneghello, Francesca, Rossi, Michele
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 21.09.2020
Témata:
ISSN:2375-5318
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We address the use of backscattered mm-wave radio signals to track humans as they move within indoor environments. The common approach in the literature leverages the extended Kalman filter (EKF) method, which however undergoes a severe performance degradation when the system evolution model is highly non-linear or presents long-term time dependencies among the system states. In this work, we propose an original model-free tracking procedure based on denoising autoencoders and sequence-to-sequence neural networks, showing its superior performance with respect to state-of-the-art methods. Our architecture can be trained in either a supervised or unsupervised manner, trading tracking accuracy for flexibility. The proposed system is tested on our own measurements, obtained with a 77 GHz radar on single and multiple subjects simultaneously moving in an indoor space. The results are compared against the ground truth trajectories from a motion tracking system, obtaining average tracking errors as low as 12 cm.
AbstractList We address the use of backscattered mm-wave radio signals to track humans as they move within indoor environments. The common approach in the literature leverages the extended Kalman filter (EKF) method, which however undergoes a severe performance degradation when the system evolution model is highly non-linear or presents long-term time dependencies among the system states. In this work, we propose an original model-free tracking procedure based on denoising autoencoders and sequence-to-sequence neural networks, showing its superior performance with respect to state-of-the-art methods. Our architecture can be trained in either a supervised or unsupervised manner, trading tracking accuracy for flexibility. The proposed system is tested on our own measurements, obtained with a 77 GHz radar on single and multiple subjects simultaneously moving in an indoor space. The results are compared against the ground truth trajectories from a motion tracking system, obtaining average tracking errors as low as 12 cm.
Author Solimini, Domenico
Rossi, Michele
Pegoraro, Jacopo
Matteo, Federico
Bashirov, Enver
Meneghello, Francesca
Author_xml – sequence: 1
  givenname: Jacopo
  surname: Pegoraro
  fullname: Pegoraro, Jacopo
  email: pegoraroja@dei.unipd.it
  organization: University of Padova,Department of Information Engineering
– sequence: 2
  givenname: Domenico
  surname: Solimini
  fullname: Solimini, Domenico
  organization: University of Padova,Department of Mathematics
– sequence: 3
  givenname: Federico
  surname: Matteo
  fullname: Matteo, Federico
  organization: University of Padova,Department of Mathematics
– sequence: 4
  givenname: Enver
  surname: Bashirov
  fullname: Bashirov, Enver
  organization: University of Padova,Department of Information Engineering
– sequence: 5
  givenname: Francesca
  surname: Meneghello
  fullname: Meneghello, Francesca
  organization: University of Padova,Department of Information Engineering
– sequence: 6
  givenname: Michele
  surname: Rossi
  fullname: Rossi, Michele
  organization: University of Padova,Department of Information Engineering
BookMark eNotj01Lw0AYhFdRsK39BV724jHx3d3s17HEagsBQSoey2bzrkbNpmxSxX9v1Z6GGR6GmSk5i31EQq4Z5IyBvXl0jUtlHwOHQthC5xw45JYrVQCckLnVhmlumLEFh1My4ULLTApmLsh0GN4ApDhEE7K8RdzRCl2KbXyhoU904f0-uRHpOjb9wa_2nYt0k5x__0W-2vGVOtp12bP7RPo35JKcB_cx4PyoM_J0t9yUq6x6uF-XiypruTRj5kyodWNUwQBANVYwH3yNUjqllPY-mIDGIzdCoyyk4iZYJZnStUAjbBAzcvXf2yLidpfazqXv7fG1-AHQzE-A
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/RadarConf2043947.2020.9266400
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 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 9781728189420
172818942X
EISSN 2375-5318
EndPage 6
ExternalDocumentID 9266400
Genre orig-research
GrantInformation_xml – fundername: MIUR (Italian Ministry of Education, University and Research)
  grantid: 232/2016
  funderid: 10.13039/501100003407
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i258t-a8fb7d86410006d931cfcbe55a6667ccf8fe8ce2837e545628f965167b3e839f3
IEDL.DBID RIE
ISICitedReferencesCount 15
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000612224900092&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 02:33:59 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i258t-a8fb7d86410006d931cfcbe55a6667ccf8fe8ce2837e545628f965167b3e839f3
OpenAccessLink https://doi.org/10.1109/RadarConf2043947.2020.9266400
PageCount 6
ParticipantIDs ieee_primary_9266400
PublicationCentury 2000
PublicationDate 2020-Sept.-21
PublicationDateYYYYMMDD 2020-09-21
PublicationDate_xml – month: 09
  year: 2020
  text: 2020-Sept.-21
  day: 21
PublicationDecade 2020
PublicationTitle Proceedings of the IEEE National Radar Conference (1996)
PublicationTitleAbbrev RadarConf20
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0053237
Score 2.2546222
Snippet We address the use of backscattered mm-wave radio signals to track humans as they move within indoor environments. The common approach in the literature...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms denoising autoencoders
Extraterrestrial measurements
human tracking
indoor sensing
mm-wave radar
Neural networks
Noise reduction
Radar tracking
sequence-to-sequence autoencoders
Spaceborne radar
Target tracking
Trajectory
Title Deep Learning for Accurate Indoor Human Tracking with a mm-Wave Radar
URI https://ieeexplore.ieee.org/document/9266400
WOSCitedRecordID wos000612224900092&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/eLvHCXMwlV1LTwIxEJ4AMUYvPsD4Tg96c2GffRyNSjQxhBgf3Eh3OjUcWAgCv992WVETL962e2jaadOZ-drvG4CLPLI29QoAiDwNUi1skKOWgeZGm4zQiLIc0Ouj6PXkYKD6Nbhac2GIqHx8Rm3_Wd7lmwkuPFTWUc6buD1Xh7oQYsXV-jp1syROxCZcVhqanSft0nBPmltxP4XLBOOwXXXwq5JK6Ui6O_8bwi60vhl5rL_2NXtQo2Iftn-ICTbh7pZoyiq91HfmglF2jbjwUhDsoTAT1y4Re-bcE3qAnHkMlmk2HgdvekmsnEwLXrp3zzf3QVUkIRjFmZwHWtpcGMlTD9Rzo5IILeaUZdolJgLRSksSyYvckI-WYmkVzyIu8oRccGSTA2gUk4IOgRnOfYQlQp1jqkJS7jQMbaJcTpUZlYZH0PQGGU5XOhjDyhbHf_8-gS1vc_-2Io5OoTGfLegMNnA5H33MzsvF-wSoRJoa
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gGh8XH2B824PeXNhHu90ejUIgIiEGlRvptlPDgYUg8Pttl_WVePG23UPTTpvOzNd-3wBcpYEx1CkAKBVTj0puvFTJxJOxlpqh0jwvB_TS4d1uMhiIXgluvrgwiJg_PsOa-8zv8vVELRxUVhfWm9g9twbrjNIwWLG1Ps9dFoUR34TrQkWz_iRtIu5ocyv2J7e5YOjXii5-1VLJXUlz93-D2IPqNyeP9L68zT6UMDuAnR9yghVo3CNOSaGY-kZsOEpulVo4MQjSzvTEtnPMnlgHpRxEThwKSyQZj71XuUSST6YKz81G_67lFWUSvFHIkrknE5NyncTUQfWxFlGgjEqRMWlTE66USQwmCp3MDbp4KUyMiFkQ8zRCGx6Z6BDK2STDIyA6jl2MxX2ZKip8FPY89E0kbFbFtKD-MVScQYbTlRLGsLDFyd-_L2Gr1X_sDDvt7sMpbDv7u5cWYXAG5flsgeewoZbz0fvsIl_ID9-TnWE
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=Proceedings+of+the+IEEE+National+Radar+Conference+%281996%29&rft.atitle=Deep+Learning+for+Accurate+Indoor+Human+Tracking+with+a+mm-Wave+Radar&rft.au=Pegoraro%2C+Jacopo&rft.au=Solimini%2C+Domenico&rft.au=Matteo%2C+Federico&rft.au=Bashirov%2C+Enver&rft.date=2020-09-21&rft.pub=IEEE&rft.eissn=2375-5318&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FRadarConf2043947.2020.9266400&rft.externalDocID=9266400