A Magnetic Field-based Ubiquitous 3D Tracking System With Physics-informed Deep Supervision Neural Network

preprint OA: closed
Full text JSON View at publisher
Full text 16,558 characters · extracted from preprint-html · click to expand
A Magnetic Field-based Ubiquitous 3D Tracking System With Physics-informed Deep Supervision Neural Network | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article A Magnetic Field-based Ubiquitous 3D Tracking System With Physics-informed Deep Supervision Neural Network Sizhen Bian, Siyu Yuan, Mengxi Liu, Hans Schotten, Paul Lukowicz This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6908305/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Precise and consistent 3D tracking is fundamental to natural user interaction and underpins a wide range of applications. While significant progress has been made across multiple sensing technologies, sustaining robust performance over time remains challenging due to accumulated drift, line-of-sight, and privacy concerns. This study introduces a near-range, infrastructure-light 3D magnetic tracking system that enables robust tracking using a compact tri-axis receiver coil, specifically designed to maximize quality factor and ensure geometric symmetry, along with spatially distributed transmitter coils. Central to our inference approach is a physics-informed deep supervision network, embedded with two key innovations: a physics-constrained output formulation and a deep multimodal supervision strategy, delivering state-of-the-art inference results with an average ATE of 2.35 cm and RTE of 3.38 cm across a wide range of hand- and head-mounted tracking tasks. The system also supports high-accuracy gesture recognition, with F1 scores of 1.000 and 0.979 for wrist and digit gestures, respectively. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Mathematics and computing/Information technology 3D Tracking Induced Magnetic Field Human Activity Recognition Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Supplementary.pdf supplementary information EntertainmentAR.mp4 Real time tracking video of interaction activity EntertainmentLego.mp4 Real time tracking video of gaming activity WritingWhiteBoard.mp4 Real time tracking video of writing activity WristGesture.mp4 Real time tracking video of wrist gesture activity workingCombined.mp4 Real time tracking video of working activity SortingHardwareTool.mp4 Real time tracking video of hardware tools sorting activity BikingCombined.mp4 Real time tracking video of biking activity SortingEverydayItem.mp4 Real time tracking video of everyday items soritng activity FingerWriting.mp4 Real time tracking video of finger air writing activity CookingCombined.mp4 Real time tracking video of cooking activity Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6908305","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":483491418,"identity":"d64128b7-ca82-41d4-892c-2b7557812419","order_by":0,"name":"Sizhen Bian","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqUlEQVRIiWNgGAWjYDACCcYGBoYKKJsELWcYGHhI0ALEjG2kaJGf3dz4uXDevTx7iQTGGx+I0WJw52Cz9MxtxcU8EgnMljOI0iKR2CDNuy0hsUcigU2ahyiHzUhs/s07B6rlDzFaGG4ktknzNkC1EKUD6Jc2a55jCcU8Zx42W/YQ5bDZ7Y9v89Qk5LG3Jx+88YMoa6AgARg7DaRoAGsZBaNgFIyCUYADAACa3S+t2b2wnwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-6760-5539","institution":"University of Kaiserslautern-Landau","correspondingAuthor":true,"prefix":"","firstName":"Sizhen","middleName":"","lastName":"Bian","suffix":""},{"id":483491419,"identity":"9d655cb9-e080-4ac6-b021-701637af70ff","order_by":1,"name":"Siyu Yuan","email":"","orcid":"","institution":"University of Kaiserslautern-Landau","correspondingAuthor":false,"prefix":"","firstName":"Siyu","middleName":"","lastName":"Yuan","suffix":""},{"id":483491420,"identity":"03fec429-6574-4d3c-8159-b11bf97883f7","order_by":2,"name":"Mengxi Liu","email":"","orcid":"","institution":"German Research Center for Artificial Intelligence","correspondingAuthor":false,"prefix":"","firstName":"Mengxi","middleName":"","lastName":"Liu","suffix":""},{"id":483491421,"identity":"30d1f060-20e4-4e7f-b8c0-1628c5008b15","order_by":3,"name":"Hans Schotten","email":"","orcid":"","institution":"University of Kaiserslautern-Landau","correspondingAuthor":false,"prefix":"","firstName":"Hans","middleName":"","lastName":"Schotten","suffix":""},{"id":483491422,"identity":"5316a0ed-315f-453d-80a0-efdde61334ab","order_by":4,"name":"Paul Lukowicz","email":"","orcid":"","institution":"University of Kaiserslautern-Landau","correspondingAuthor":false,"prefix":"","firstName":"Paul","middleName":"","lastName":"Lukowicz","suffix":""}],"badges":[],"createdAt":"2025-06-16 19:55:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6908305/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6908305/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104406233,"identity":"8ef9ab0f-2c51-4272-a662-54ea67724cd6","added_by":"auto","created_at":"2026-03-11 12:25:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2553451,"visible":true,"origin":"","legend":"Article File","description":"","filename":"MagToBeSubmitted.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1_covered_d04585ab-45c8-4e4f-a831-6824931b7bb9.pdf"},{"id":86624890,"identity":"7c5765c4-c839-4cb3-a60f-2f8e69471c74","added_by":"auto","created_at":"2025-07-14 04:59:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2041898,"visible":true,"origin":"","legend":"supplementary information","description":"","filename":"Supplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/67273c1a53e475fdd54d5a65.pdf"},{"id":86624894,"identity":"544a46b9-e1e8-4571-adbf-1e259ea1809b","added_by":"auto","created_at":"2025-07-14 04:59:51","extension":"mp4","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":19352978,"visible":true,"origin":"","legend":"Real time tracking video of interaction activity","description":"","filename":"EntertainmentAR.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/c8c2a28991b29dbab5dd3b24.mp4"},{"id":86625068,"identity":"b3664419-e9fe-4719-85f3-aabede631904","added_by":"auto","created_at":"2025-07-14 05:07:50","extension":"mp4","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":35604072,"visible":true,"origin":"","legend":"Real time tracking video of gaming activity","description":"","filename":"EntertainmentLego.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/541847ad00c6e15de2744fc9.mp4"},{"id":86624892,"identity":"adc38ba3-6f57-469e-b110-759e013958f7","added_by":"auto","created_at":"2025-07-14 04:59:51","extension":"mp4","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":43288011,"visible":true,"origin":"","legend":"Real time tracking video of writing activity","description":"","filename":"WritingWhiteBoard.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/92bb96a39f309f0b91419989.mp4"},{"id":86624898,"identity":"7038586a-addd-4098-a590-59270fbe5b53","added_by":"auto","created_at":"2025-07-14 04:59:51","extension":"mp4","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":51757721,"visible":true,"origin":"","legend":"Real time tracking video of wrist gesture activity","description":"","filename":"WristGesture.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/f4ae6327d15678205c5db829.mp4"},{"id":86624897,"identity":"101f9e96-cb02-47ac-ab74-05b2e7e92537","added_by":"auto","created_at":"2025-07-14 04:59:51","extension":"mp4","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":67710284,"visible":true,"origin":"","legend":"Real time tracking video of working activity","description":"","filename":"workingCombined.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/e8af7a642349d7dffdf22a57.mp4"},{"id":86624896,"identity":"dc31dd4f-863d-4e32-9033-153703fc1c93","added_by":"auto","created_at":"2025-07-14 04:59:51","extension":"mp4","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":83634217,"visible":true,"origin":"","legend":"Real time tracking video of hardware tools sorting activity","description":"","filename":"SortingHardwareTool.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/eac3c0cddf813b9406d1e632.mp4"},{"id":86624900,"identity":"3d6a29ac-a394-4688-9c36-3fa9835ff58a","added_by":"auto","created_at":"2025-07-14 04:59:52","extension":"mp4","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":91486569,"visible":true,"origin":"","legend":"Real time tracking video of biking activity","description":"","filename":"BikingCombined.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/77d2ed217abbfeeaa97f62ad.mp4"},{"id":86624899,"identity":"8a25544b-cf2c-48a6-8eac-3262ef83f38f","added_by":"auto","created_at":"2025-07-14 04:59:51","extension":"mp4","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":102161967,"visible":true,"origin":"","legend":"Real time tracking video of everyday items soritng activity","description":"","filename":"SortingEverydayItem.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/80a74b04c7e9269b616ed083.mp4"},{"id":86624901,"identity":"4def32dd-3fd1-4479-92da-d7ebe351950e","added_by":"auto","created_at":"2025-07-14 04:59:53","extension":"mp4","order_by":10,"title":"","display":"","copyAsset":false,"role":"supplement","size":197465567,"visible":true,"origin":"","legend":"Real time tracking video of finger air writing activity","description":"","filename":"FingerWriting.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/bf723863e3da8f0bc52fd4c2.mp4"},{"id":86624903,"identity":"11c938b3-76ab-46cb-8329-cd9dd5a0d824","added_by":"auto","created_at":"2025-07-14 04:59:55","extension":"mp4","order_by":11,"title":"","display":"","copyAsset":false,"role":"supplement","size":261386230,"visible":true,"origin":"","legend":"Real time tracking video of cooking activity","description":"","filename":"CookingCombined.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6908305/v1/ecae5f407a4e8159adb8911e.mp4"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A Magnetic Field-based Ubiquitous 3D Tracking System With Physics-informed Deep Supervision Neural Network","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"3D Tracking, Induced Magnetic Field, Human Activity Recognition","lastPublishedDoi":"10.21203/rs.3.rs-6908305/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6908305/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Precise and consistent 3D tracking is fundamental to natural user interaction and underpins a wide range of applications. While significant progress has been made across multiple sensing technologies, sustaining robust performance over time remains challenging due to accumulated drift, line-of-sight, and privacy concerns. This study introduces a near-range, infrastructure-light 3D magnetic tracking system that enables robust tracking using a compact tri-axis receiver coil, specifically designed to maximize quality factor and ensure geometric symmetry, along with spatially distributed transmitter coils. Central to our inference approach is a physics-informed deep supervision network, embedded with two key innovations: a physics-constrained output formulation and a deep multimodal supervision strategy, delivering state-of-the-art inference results with an average ATE of 2.35 cm and RTE of 3.38 cm across a wide range of hand- and head-mounted tracking tasks. The system also supports high-accuracy gesture recognition, with F1 scores of 1.000 and 0.979 for wrist and digit gestures, respectively.","manuscriptTitle":"A Magnetic Field-based Ubiquitous 3D Tracking System With Physics-informed Deep Supervision Neural Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-14 04:59:45","doi":"10.21203/rs.3.rs-6908305/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e9cd39fa-b22b-4610-8d73-9dd9aa27cb36","owner":[],"postedDate":"July 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":51337791,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":51337792,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2026-03-11T01:56:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-14 04:59:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6908305","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6908305","identity":"rs-6908305","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00