M2S2: A Multimodal Sensor System for Remote Animal Motion Capture in the Wild

Capturing animal locomotion in the wild is far more challenging than in controlled laboratory settings. Wildlife subjects move unpredictably, and issues, such as scaling, occlusion, lighting changes, and the lack of ground truth data, make motion capture difficult. Unlike human biomechanics, where m...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE sensors letters Ročník 9; číslo 4; s. 1 - 4
Hlavní autoři: Vally, Azraa, Maswoswere, Gerald, Bowden, Nicholas, Paine, Stephen, Amayo, Paul, Markham, Andrew, Patel, Amir
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.04.2025
Témata:
ISSN:2475-1472, 2475-1472
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Capturing animal locomotion in the wild is far more challenging than in controlled laboratory settings. Wildlife subjects move unpredictably, and issues, such as scaling, occlusion, lighting changes, and the lack of ground truth data, make motion capture difficult. Unlike human biomechanics, where machine learning thrives with annotated datasets, such resources are scarce for wildlife. Multimodal sensing offers a solution by combining the strengths of various sensors, such as Light Detection and Ranging {LiDAR) and thermal cameras, to compensate for individual sensor limitations. In addition, some sensors, like LiDAR, can provide training data for monocular pose estimation models. We introduce a multimodal sensor system (M2S2) for capturing animal motion in the wild. M2S2 integrates RGB, depth, thermal, event, LiDAR, and acoustic sensors to overcome challenges like synchronization and calibration. We showcase its application with data from cheetahs, offering a new resource for advancing sensor fusion algorithms in wildlife motion capture.
AbstractList Capturing animal locomotion in the wild is far more challenging than in controlled laboratory settings. Wildlife subjects move unpredictably, and issues, such as scaling, occlusion, lighting changes, and the lack of ground truth data, make motion capture difficult. Unlike human biomechanics, where machine learning thrives with annotated datasets, such resources are scarce for wildlife. Multimodal sensing offers a solution by combining the strengths of various sensors, such as Light Detection and Ranging {LiDAR) and thermal cameras, to compensate for individual sensor limitations. In addition, some sensors, like LiDAR, can provide training data for monocular pose estimation models. We introduce a multimodal sensor system (M2S2) for capturing animal motion in the wild. M2S2 integrates RGB, depth, thermal, event, LiDAR, and acoustic sensors to overcome challenges like synchronization and calibration. We showcase its application with data from cheetahs, offering a new resource for advancing sensor fusion algorithms in wildlife motion capture.
Author Paine, Stephen
Bowden, Nicholas
Amayo, Paul
Maswoswere, Gerald
Markham, Andrew
Patel, Amir
Vally, Azraa
Author_xml – sequence: 1
  givenname: Azraa
  orcidid: 0000-0002-0117-6943
  surname: Vally
  fullname: Vally, Azraa
  email: vllazr002@myuct.ac.za
  organization: Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa
– sequence: 2
  givenname: Gerald
  orcidid: 0009-0005-1444-5953
  surname: Maswoswere
  fullname: Maswoswere, Gerald
  email: mswger001@myuct.ac.za
  organization: Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa
– sequence: 3
  givenname: Nicholas
  surname: Bowden
  fullname: Bowden, Nicholas
  organization: Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa
– sequence: 4
  givenname: Stephen
  orcidid: 0000-0001-8621-7005
  surname: Paine
  fullname: Paine, Stephen
  organization: Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa
– sequence: 5
  givenname: Paul
  orcidid: 0000-0002-6681-8230
  surname: Amayo
  fullname: Amayo, Paul
  organization: Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa
– sequence: 6
  givenname: Andrew
  orcidid: 0000-0001-5716-3941
  surname: Markham
  fullname: Markham, Andrew
  organization: Department of Computer Science, University of Oxford, Oxford, U.K
– sequence: 7
  givenname: Amir
  orcidid: 0000-0002-2344-4179
  surname: Patel
  fullname: Patel, Amir
  organization: Department of Electrical Engineering, University of Cape Town, Cape Town, South Africa
BookMark eNpNkM1Kw0AUhQepYK19AXExL5A6904yM3FXSv2BRsEoLkPS3MFIkimZ6aJvb6pddHUPXL7D4btmk971xNgtiAWASO83-fo1X6DAZCGTGFHKCzbFWCcRxBonZ_mKzb3_EUKAQS2kmLIswxwf-JJn-zY0navLlufUezfw_OADddyO8Z06F4gv-6Yb_5kLjev5qtyF_UC86Xn4Jv7VtPUNu7Rl62l-ujP2-bj-WD1Hm7enl9VyE20RIUSkDGiFilCDqYyqSFgEMtsUgGoRp6WurUKTlClJELWA1FbC2nFxUspKyRnD_97t4LwfyBa7YZw2HAoQxdFJ8eekODopTk5G6O4faojoDDBGo1TyFzLKXaA
CODEN ISLECD
Cites_doi 10.1109/CVPRW53098.2021.00155
10.1007/978-3-030-58621-8_12
10.1117/12.829094
10.1109/JSTSP.2021.3061270
10.3389/fnbeh.2021.637806
10.3390/s23073479
10.1109/CVPR.2018.00790
10.1007/978-3-030-58523-5_1
10.1109/ICCV.2019.00546
10.1109/CVPR42600.2020.00836
10.1109/CVPRW59228.2023.00022
10.1038/s41592-021-01106-6
10.1109/IROS.2018.8593660
10.1109/CVPR42600.2020.00502
10.1109/WACV48630.2021.00190
10.1109/ICCV51070.2023.00835
10.1007/s11263-022-01714-5
10.1109/ACCESS.2023.3264714
10.1007/978-3-319-08651-4_1
10.3390/electronics12163423
10.3389/fnbeh.2020.581154
10.1109/ICRA48506.2021.9561338
10.1038/s41467-020-18441-5
10.1145/3560905.3567770
10.1038/s42256-022-00520-5
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/LSENS.2025.3542233
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISSN 2475-1472
EndPage 4
ExternalDocumentID 10_1109_LSENS_2025_3542233
10887236
Genre orig-research
GroupedDBID 0R~
6IK
97E
AAJGR
AASAJ
AAWTH
ABAZT
ABJNI
ABQJQ
ABVLG
ACGFS
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
OCL
RIA
RIE
AAYXX
CITATION
ID FETCH-LOGICAL-c221t-e6817626e2718b86be0f21e8c911ed049a7df6285a9e310d019fb0ff0305a3b63
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001445056900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2475-1472
IngestDate Sat Nov 29 08:09:15 EST 2025
Wed Aug 27 01:47:41 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c221t-e6817626e2718b86be0f21e8c911ed049a7df6285a9e310d019fb0ff0305a3b63
ORCID 0000-0002-0117-6943
0000-0001-8621-7005
0000-0002-2344-4179
0000-0002-6681-8230
0009-0005-1444-5953
0000-0001-5716-3941
PageCount 4
ParticipantIDs crossref_primary_10_1109_LSENS_2025_3542233
ieee_primary_10887236
PublicationCentury 2000
PublicationDate 2025-04-01
PublicationDateYYYYMMDD 2025-04-01
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-01
  day: 01
PublicationDecade 2020
PublicationTitle IEEE sensors letters
PublicationTitleAbbrev LSENS
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref15
Feti (ref34) 2012
ref14
ref31
ref11
ref33
ref10
An (ref8) 2022
ref2
ref1
ref17
ref16
ref19
ref18
(ref32) 2024
ref24
ref23
Zanfir (ref26) 2023
ref25
ref20
Ci (ref28) 2022
ref22
ref21
ref27
(ref29) 2023
ref7
Yang (ref12) 2022
(ref30) 2023
ref9
ref4
ref6
ref5
Yang (ref3) 2023; 36
References_xml – ident: ref33
  doi: 10.1109/CVPRW53098.2021.00155
– start-page: 17301
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2022
  ident: ref12
  article-title: APT-36K: A large-scale benchmark for animal pose estimation and tracking
– ident: ref17
  doi: 10.1007/978-3-030-58621-8_12
– ident: ref15
  doi: 10.1117/12.829094
– ident: ref4
  doi: 10.1109/JSTSP.2021.3061270
– ident: ref14
  doi: 10.3389/fnbeh.2021.637806
– start-page: 1114
  volume-title: Proc. Conf. Robot Learn.
  year: 2023
  ident: ref26
  article-title: HUM3DIL: Semi-supervised multi-modal 3D human pose estimation for autonomous driving
– ident: ref24
  doi: 10.3390/s23073479
– ident: ref27
  doi: 10.1109/CVPR.2018.00790
– ident: ref11
  doi: 10.1007/978-3-030-58523-5_1
– ident: ref21
  doi: 10.1109/ICCV.2019.00546
– start-page: 1752
  volume-title: Proc. 35th Int. Conv. MIPRO
  year: 2012
  ident: ref34
  article-title: The procedure of a camera calibration using camera calibration toolbox for MATLAB
– volume-title: LiDAR camera calibrator app
  year: 2024
  ident: ref32
– ident: ref23
  doi: 10.1109/CVPR42600.2020.00836
– volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops
  year: 2022
  ident: ref28
  article-title: The sound of motion: Multimodal horse motion estimation from video and audio
– ident: ref5
  doi: 10.1109/CVPRW59228.2023.00022
– ident: ref13
  doi: 10.1038/s41592-021-01106-6
– year: 2023
  ident: ref29
  article-title: ROS 2: Robot operating system 2
– year: 2023
  ident: ref30
  article-title: eCAL: Efficient communication abstraction layer
– volume: 36
  start-page: 18756
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2023
  ident: ref3
  article-title: MM-Fi: Multi-modal non-intrusive 4D human dataset for versatile wireless sensing
– ident: ref31
  doi: 10.1109/IROS.2018.8593660
– ident: ref25
  doi: 10.1109/CVPR42600.2020.00502
– ident: ref10
  doi: 10.1109/WACV48630.2021.00190
– start-page: 27414
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2022
  ident: ref8
  article-title: mRI: Multi-modal 3D human pose estimation dataset using mmWave, RGB-D, and inertial sensors
– ident: ref18
  doi: 10.1109/ICCV51070.2023.00835
– ident: ref19
  doi: 10.1007/s11263-022-01714-5
– ident: ref1
  doi: 10.1109/ACCESS.2023.3264714
– ident: ref22
  doi: 10.1007/978-3-319-08651-4_1
– ident: ref7
  doi: 10.3390/electronics12163423
– ident: ref9
  doi: 10.3389/fnbeh.2020.581154
– ident: ref20
  doi: 10.1109/ICRA48506.2021.9561338
– ident: ref16
  doi: 10.1038/s41467-020-18441-5
– ident: ref6
  doi: 10.1145/3560905.3567770
– ident: ref2
  doi: 10.1038/s42256-022-00520-5
SSID ssj0001827030
Score 2.2944179
Snippet Capturing animal locomotion in the wild is far more challenging than in controlled laboratory settings. Wildlife subjects move unpredictably, and issues, such...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 1
SubjectTerms Animals
Calibration
Cameras
Laser radar
Motion capture
Pose estimation
Radar
sensor fusion
Sensor systems
Sensors
Synchronization
Thermal sensors
Title M2S2: A Multimodal Sensor System for Remote Animal Motion Capture in the Wild
URI https://ieeexplore.ieee.org/document/10887236
Volume 9
WOSCitedRecordID wos001445056900001&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2475-1472
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001827030
  issn: 2475-1472
  databaseCode: RIE
  dateStart: 20170101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxcDCQxRRXvLAhlISJ_GDrapaMdAKEZC6RXF8ljo0qUrL7-fspKIMDGxR4kjRd7m7z_Z9PkLuCyuTwnBkbq7KIRGhCZS0OogSbUsdWsVL6ZtNiNlMzufqtRWrey0MAPjiMxi4S7-Xb-py65bK0MPRJVjMO6QjBG_EWj8LKpK5v3cnjAnV40s2nmU4BWTpIE4TzIPxr-Sz103FJ5PJyT8_45Qct6yRDhszn5EDqM7JdMoy9kSH1Itol7XBERnOSus1bc4hp0hI6RugMYAOq8USn0990x46KlZu54AuKooEkGJoMD3yMRm_j56DtjtCUDIWbQLgMsJIxoFhetGSawgti0CWGL7AIPEvhLFOIFkoQA5nkMtZBN86Dy9izeML0q3qCi4JFaVSGiBNNSZ05Bs6FlZCZAsJWsk46ZOHHWz5qjkEI_eTh1DlHuTcgZy3IPdJz2G2N7KB6-qP-9fkyL3elMPckO5mvYVbclh-bRaf6ztv5G9riaTj
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagIMHCQxRRnh7YUErivGy2CrUqookQLVK3KI7PUocmVWn5_ZydVJSBgS1KrCj6Lnf32b7PR8h9rnmQqwiZm6lyCGJXOYJr6XiB1IV0tYgKbptNxGnKp1Px1ojVrRYGAGzxGXTNpd3LV1WxNktl6OHoEsyPdsmeaZ3VyLV-llQ4M__vRhrjisfRuJ-OcRLIwq4fBpgJ_V_pZ6ufik0ng-N_fsgJOWp4I-3Vhj4lO1CekSRhY_ZEe9TKaOeVwhFjnJdWS1qfRE6RktJ3QHMA7ZWzOT5PbNse-pwvzN4BnZUUKSDF4KDa5GPQnzwPnaY_glMw5q0ciLiHsSwChglG8kiCq5kHvMAABgqpfx4rbSSSuQBkcQrZnEb4tfHx3JeRf05aZVXCBaFxIYQECEOJKR0Zh_RjzcHTOQcpuB90yMMGtmxRH4OR2emDKzILcmZAzhqQO6RtMNsaWcN1-cf9O3IwnCSjbPSSvl6RQ_OqujjmmrRWyzXckP3iazX7XN5ag38DNdioLA
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%3Ajournal&rft.genre=article&rft.atitle=M2S2%3A+A+Multimodal+Sensor+System+for+Remote+Animal+Motion+Capture+in+the+Wild&rft.jtitle=IEEE+sensors+letters&rft.au=Vally%2C+Azraa&rft.au=Maswoswere%2C+Gerald&rft.au=Bowden%2C+Nicholas&rft.au=Paine%2C+Stephen&rft.date=2025-04-01&rft.issn=2475-1472&rft.eissn=2475-1472&rft.volume=9&rft.issue=4&rft.spage=1&rft.epage=4&rft_id=info:doi/10.1109%2FLSENS.2025.3542233&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LSENS_2025_3542233
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2475-1472&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2475-1472&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2475-1472&client=summon