Mostrar el registro sencillo del ítem

dc.contributor.authorChmurski, Mateusz
dc.contributor.authorMauro, Gianfranco
dc.contributor.authorSantra, Avik
dc.contributor.authorZubert, Mariusz
dc.contributor.authorDagasan, Gökberk
dc.date.accessioned2021-11-09T11:24:59Z
dc.date.available2021-11-09T11:24:59Z
dc.date.issued2021
dc.identifier.citationChmurski, M.; Mauro, G.; Santra, A.; Zubert, M.; Dagasan, G. Highly-Optimized Radar-Based Gesture Recognition System with Depthwise Expansion Module. Sensors 2021, 21, 7298. https:// doi.org/10.3390/s21217298es_ES
dc.identifier.urihttp://hdl.handle.net/10481/71388
dc.description.abstractThe increasing integration of technology in our daily lives demands the development of more convenient human–computer interaction (HCI) methods. Most of the current hand-based HCI strategies exhibit various limitations, e.g., sensibility to variable lighting conditions and limitations on the operating environment. Further, the deployment of such systems is often not performed in resource-constrained contexts. Inspired by the MobileNetV1 deep learning network, this paper presents a novel hand gesture recognition system based on frequency-modulated continuous wave (FMCW) radar, exhibiting a higher recognition accuracy in comparison to the state-of-the-art systems. First of all, the paper introduces a method to simplify radar preprocessing while preserving the main information of the performed gestures. Then, a deep neural classifier with the novel Depthwise Expansion Module based on the depthwise separable convolutions is presented. The introduced classifier is optimized and deployed on the Coral Edge TPU board. The system defines and adopts eight different hand gestures performed by five users, offering a classification accuracy of 98.13% while operating in a low-power and resource-constrained environment.es_ES
dc.description.sponsorshipElectronic Components and Systems for European Leadership Joint Undertaking under grant agreement No. 826655 (Tempo).es_ES
dc.description.sponsorshipEuropean Union’s Horizon 2020 research and innovation programme and Belgium, France, Germany, Switzerland, and the Netherlandses_ES
dc.description.sponsorshipLodz University of Technology.es_ES
dc.language.isoenges_ES
dc.publisherMDPIes_ES
dc.rightsAtribución 3.0 España*
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/*
dc.subjectEdge computinges_ES
dc.subjectEdge TPUes_ES
dc.subjectOptimizationes_ES
dc.subjectQuantizationes_ES
dc.subjectFMCWes_ES
dc.subjectRadar es_ES
dc.subjectDeep learninges_ES
dc.subjectNeural networkses_ES
dc.titleHighly-Optimized Radar-Based Gesture Recognition System with Depthwise Expansion Modulees_ES
dc.typejournal articlees_ES
dc.rights.accessRightsopen accesses_ES
dc.identifier.doi10.3390/s21217298


Ficheros en el ítem

[PDF]

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Atribución 3.0 España
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución 3.0 España