Accelerometer-based hand gesture recognition system for Interaction in digital TV

Fil: Ducloux, José. Universidad Católica de Córdoba. Facultad de Ingeniería; Argentina

Guardado en:
Detalles Bibliográficos
Autores principales: Ducloux, José, Colla, Pedro, Petrashin, Pablo, Lancioni, Walter, Toledo, Luis
Formato: conferenceObject
Lenguaje:Inglés
Publicado: 2023
Materias:
Remote control
Human-machine interaction
Multilayer perceptron (MLP)
Support vector machine (SVM)
Acceso en línea:http://hdl.handle.net/11086/546344
Aporte de:
Repositorio Digital Universitario (UNC) de Universidad Nacional de Córdoba
id I10-R141-11086-546344
record_format dspace
spelling I10-R141-11086-5463442023-08-30T13:56:40Z Accelerometer-based hand gesture recognition system for Interaction in digital TV Ducloux, José Colla, Pedro Petrashin, Pablo Lancioni, Walter Toledo, Luis Remote control Human-machine interaction Multilayer perceptron (MLP) Support vector machine (SVM) Fil: Ducloux, José. Universidad Católica de Córdoba. Facultad de Ingeniería; Argentina Fil: Ducloux, José. Instituto Universitario Aeronáutico. Especialización en Sistemas Embebidos; Argentina. Fil: Ducloux, José. Consorcio Córdoba TDT; Argentina. Fil: Colla, Pedro. Instituto Universitario Aeronáutico. Especialización en Sistemas Embebidos; Argentina. Fil: Petrashin, Pablo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas Físicas y Naturales. Carrera de Ingeniería Electrónica; Argentina. Fil: Petrashin, Pablo. Universidad Cátólica de Córdoba. Facultad de Ingeniería; Argentina. Fil: Lancioni, Walter. Universidad Cátólica de Córdoba. Facultad de Ingeniería; Argentina. Fil: Toledo, Luis. Universidad Cátólica de Córdoba. Facultad de Ingeniería; Argentina. This paper presents the design and implementation of a system of accelerometer-based hand gesture recognition. This system will be embedded within a modern remote control to improve human-machine interaction in the context of digital TV of Argentina. As the recognition of hand gestures is a pattern classification problem, two techniques based on artificial neural networks are explored: multilayer perceptron and support vector machine. This is performed in order to compare results and select the tool that best fits the problem. Jointly, signal digital processing techniques are used for preprocessing and adapting of the input signals to pattern recognition models. A gestural vocabulary of 8 types of gestures was used, which was also used by other similar works in order to compare results. An appropriate trade-off between the classifier recognition precision and resource utilization of the hardware platform is required in order to implement the solution within an embedded system. The obtained results of precision and utilization of resources are excellent. Fil: Ducloux, José. Universidad Católica de Córdoba. Facultad de Ingeniería; Argentina Fil: Ducloux, José. Instituto Universitario Aeronáutico. Especialización en Sistemas Embebidos; Argentina. Fil: Ducloux, José. Consorcio Córdoba TDT; Argentina. Fil: Colla, Pedro. Instituto Universitario Aeronáutico. Especialización en Sistemas Embebidos; Argentina. Fil: Petrashin, Pablo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas Físicas y Naturales. Carrera de Ingeniería Electrónica; Argentina. Fil: Petrashin, Pablo. Universidad Cátólica de Córdoba. Facultad de Ingeniería; Argentina. Fil: Lancioni, Walter. Universidad Cátólica de Córdoba. Facultad de Ingeniería; Argentina. Fil: Toledo, Luis. Universidad Cátólica de Córdoba. Facultad de Ingeniería; Argentina. Sistemas de Automatización y Control 2023-03-01T14:11:21Z 2023-03-01T14:11:21Z 2014 conferenceObject http://hdl.handle.net/11086/546344 eng Attribution-NonCommercial-ShareAlike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/ Impreso
institution Universidad Nacional de Córdoba
institution_str I-10
repository_str R-141
collection Repositorio Digital Universitario (UNC)
language Inglés
topic Remote control
Human-machine interaction
Multilayer perceptron (MLP)
Support vector machine (SVM)
spellingShingle Remote control
Human-machine interaction
Multilayer perceptron (MLP)
Support vector machine (SVM)
Ducloux, José
Colla, Pedro
Petrashin, Pablo
Lancioni, Walter
Toledo, Luis
Accelerometer-based hand gesture recognition system for Interaction in digital TV
topic_facet Remote control
Human-machine interaction
Multilayer perceptron (MLP)
Support vector machine (SVM)
description Fil: Ducloux, José. Universidad Católica de Córdoba. Facultad de Ingeniería; Argentina
format conferenceObject
author Ducloux, José
Colla, Pedro
Petrashin, Pablo
Lancioni, Walter
Toledo, Luis
author_facet Ducloux, José
Colla, Pedro
Petrashin, Pablo
Lancioni, Walter
Toledo, Luis
author_sort Ducloux, José
title Accelerometer-based hand gesture recognition system for Interaction in digital TV
title_short Accelerometer-based hand gesture recognition system for Interaction in digital TV
title_full Accelerometer-based hand gesture recognition system for Interaction in digital TV
title_fullStr Accelerometer-based hand gesture recognition system for Interaction in digital TV
title_full_unstemmed Accelerometer-based hand gesture recognition system for Interaction in digital TV
title_sort accelerometer-based hand gesture recognition system for interaction in digital tv
publishDate 2023
url http://hdl.handle.net/11086/546344
work_keys_str_mv AT duclouxjose accelerometerbasedhandgesturerecognitionsystemforinteractionindigitaltv
AT collapedro accelerometerbasedhandgesturerecognitionsystemforinteractionindigitaltv
AT petrashinpablo accelerometerbasedhandgesturerecognitionsystemforinteractionindigitaltv
AT lancioniwalter accelerometerbasedhandgesturerecognitionsystemforinteractionindigitaltv
AT toledoluis accelerometerbasedhandgesturerecognitionsystemforinteractionindigitaltv
_version_ 1782014114469511168

Ejemplares similares