A machine learning approach for gesture recognition with a lensless smart sensor system

Simple item page
dc.contributor.authorNormani, Niccolo
dc.contributor.authorUrru, Andrea
dc.contributor.authorAbraham, Lizy
dc.contributor.authorWalsh, Michael
dc.contributor.authorTedesco, Salvatore
dc.contributor.authorCenedese, A.
dc.contributor.authorSusto, Gian Antoino
dc.contributor.authorO'Flynn, Brendan
dc.contributor.funderScience Foundation Irelanden
dc.contributor.funderEuropean Regional Development Funden
dc.date.accessioned2018-10-12T14:59:23Z
dc.date.available2018-10-12T14:59:23Z
dc.date.issued2018-03
dc.date.updated2018-10-12T14:53:34Z
dc.description.abstractHand motion tracking traditionally requires highly complex and expensive systems in terms of energy and computational demands. A low-power, low-cost system could lead to a revolution in this field as it would not require complex hardware while representing an infrastructure-less ultra-miniature (~ 100μm - [1]) solution. The present paper exploits the Multiple Point Tracking algorithm developed at the Tyndall National Institute as the basic algorithm to perform a series of gesture recognition tasks. The hardware relies upon the combination of a stereoscopic vision of two novel Lensless Smart Sensors (LSS) combined with IR filters and five hand-held LEDs to track. Tracking common gestures generates a six-gestures dataset, which is then employed to train three Machine Learning models: k-Nearest Neighbors, Support Vector Machine and Random Forest. An offline analysis highlights how different LEDs' positions on the hand affect the classification accuracy. The comparison shows how the Random Forest outperforms the other two models with a classification accuracy of 90-91 %.en
dc.description.sponsorship13/RC/2077en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationNormani, N., Urru, A., Abraham, L., Walsh, M., Tedesco, S., Cenedese, A., Susto, G. A. and O'Flynn, B. (2018) 'A machine learning approach for gesture recognition with a lensless smart sensor system', 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks (BSN), Las Vegas, NV, USA, 4-7 March, pp. 136-139. doi: 10.1109/BSN.2018.8329677en
dc.identifier.doi10.1109/BSN.2018.8329677
dc.identifier.endpage139en
dc.identifier.isbn978-1-5386-1109-8
dc.identifier.isbn978-1-5386-1110-4
dc.identifier.startpage136en
dc.identifier.urihttps://hdl.handle.net/10468/7008
dc.language.isoenen
dc.relation.ispartof2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks (BSN)
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/13/RC/2077/IE/CONNECT: The Centre for Future Networks & Communications/en
dc.relation.urihttps://ieeexplore.ieee.org/document/8329677
dc.rights© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectComputer visionen
dc.subjectDigital filtersen
dc.subjectGesture recognitionen
dc.subjectImage motion analysisen
dc.subjectIntelligent sensorsen
dc.subjectLearning (artificial intelligence)en
dc.subjectLight emitting diodesen
dc.subjectObject trackingen
dc.subjectStereo image processingen
dc.subjectSupport vector machinesen
dc.subjectRandom Foresten
dc.subjectMachine learning approachen
dc.subjectLensless smart sensor systemen
dc.subjectHand motion trackingen
dc.subjectComputational demandsen
dc.subjectLow-cost systemen
dc.subjectComplex hardwareen
dc.subjectMultiple Point Tracking algorithmen
dc.subjectTyndall National Instituteen
dc.subjectGesture recognition tasksen
dc.subjectStereoscopic visionen
dc.subjectIR filtersen
dc.subjectTracking common gesturesen
dc.subjectSix-gestures dataseten
dc.subjectMachine Learning modelsen
dc.subjectSupport Vector Machineen
dc.subjectLow-power systemen
dc.subjectInfrastructure-less ultra-miniature solutionen
dc.subjectHand-held LEDen
dc.subjectk-Nearest Neighborsen
dc.subjectSensorsen
dc.subjectHardwareen
dc.subjectRadio frequencyen
dc.subjectCalibrationen
dc.subjectLensless Smart Sensoren
dc.subjectMachine Learningen
dc.titleA machine learning approach for gesture recognition with a lensless smart sensor systemen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
6519_BSN2018.pdf
Size:
932.33 KB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Tyndall National Institute - Conference Items