Gesture-Based Human Machine Interaction Using RCNNs in Limited Computation Power Devices
The use of gestures is one of the main forms of human machine interaction (HMI) in many fields, from advanced robotics industrial setups, to multimedia devices at home. Almost every gesture detection system uses computer vision as the fundamental technology, with the already well-known problems of i...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/24/8202 |
_version_ | 1797500863037571072 |
---|---|
author | Alberto Tellaeche Iglesias Ignacio Fidalgo Astorquia Juan Ignacio Vázquez Gómez Surajit Saikia |
author_facet | Alberto Tellaeche Iglesias Ignacio Fidalgo Astorquia Juan Ignacio Vázquez Gómez Surajit Saikia |
author_sort | Alberto Tellaeche Iglesias |
collection | DOAJ |
description | The use of gestures is one of the main forms of human machine interaction (HMI) in many fields, from advanced robotics industrial setups, to multimedia devices at home. Almost every gesture detection system uses computer vision as the fundamental technology, with the already well-known problems of image processing: changes in lighting conditions, partial occlusions, variations in color, among others. To solve all these potential issues, deep learning techniques have been proven to be very effective. This research proposes a hand gesture recognition system based on convolutional neural networks and color images that is robust against environmental variations, has a real time performance in embedded systems, and solves the principal problems presented in the previous paragraph. A new CNN network has been specifically designed with a small architecture in terms of number of layers and total number of neurons to be used in computationally limited devices. The obtained results achieve a percentage of success of 96.92% on average, a better score than those obtained by previous algorithms discussed in the state of the art. |
first_indexed | 2024-03-10T03:09:58Z |
format | Article |
id | doaj.art-b6b5777b2e744d8791d0d9714ae7541e |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T03:09:58Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-b6b5777b2e744d8791d0d9714ae7541e2023-11-23T10:28:08ZengMDPI AGSensors1424-82202021-12-012124820210.3390/s21248202Gesture-Based Human Machine Interaction Using RCNNs in Limited Computation Power DevicesAlberto Tellaeche Iglesias0Ignacio Fidalgo Astorquia1Juan Ignacio Vázquez Gómez2Surajit Saikia3Computer Science, Electronics and Communication Technologies Department, University of Deusto, Avenida de las Universidades 24, 48007 Bilbao, SpainDeustoTech-Deusto Institute of Technology, University of Deusto, Avenida de las Universidades 24, 48007 Bilbao, SpainComputer Science, Electronics and Communication Technologies Department, University of Deusto, Avenida de las Universidades 24, 48007 Bilbao, SpainDeustoTech-Deusto Institute of Technology, University of Deusto, Avenida de las Universidades 24, 48007 Bilbao, SpainThe use of gestures is one of the main forms of human machine interaction (HMI) in many fields, from advanced robotics industrial setups, to multimedia devices at home. Almost every gesture detection system uses computer vision as the fundamental technology, with the already well-known problems of image processing: changes in lighting conditions, partial occlusions, variations in color, among others. To solve all these potential issues, deep learning techniques have been proven to be very effective. This research proposes a hand gesture recognition system based on convolutional neural networks and color images that is robust against environmental variations, has a real time performance in embedded systems, and solves the principal problems presented in the previous paragraph. A new CNN network has been specifically designed with a small architecture in terms of number of layers and total number of neurons to be used in computationally limited devices. The obtained results achieve a percentage of success of 96.92% on average, a better score than those obtained by previous algorithms discussed in the state of the art.https://www.mdpi.com/1424-8220/21/24/8202real timedeep learninggesture detectionembedded systems |
spellingShingle | Alberto Tellaeche Iglesias Ignacio Fidalgo Astorquia Juan Ignacio Vázquez Gómez Surajit Saikia Gesture-Based Human Machine Interaction Using RCNNs in Limited Computation Power Devices Sensors real time deep learning gesture detection embedded systems |
title | Gesture-Based Human Machine Interaction Using RCNNs in Limited Computation Power Devices |
title_full | Gesture-Based Human Machine Interaction Using RCNNs in Limited Computation Power Devices |
title_fullStr | Gesture-Based Human Machine Interaction Using RCNNs in Limited Computation Power Devices |
title_full_unstemmed | Gesture-Based Human Machine Interaction Using RCNNs in Limited Computation Power Devices |
title_short | Gesture-Based Human Machine Interaction Using RCNNs in Limited Computation Power Devices |
title_sort | gesture based human machine interaction using rcnns in limited computation power devices |
topic | real time deep learning gesture detection embedded systems |
url | https://www.mdpi.com/1424-8220/21/24/8202 |
work_keys_str_mv | AT albertotellaecheiglesias gesturebasedhumanmachineinteractionusingrcnnsinlimitedcomputationpowerdevices AT ignaciofidalgoastorquia gesturebasedhumanmachineinteractionusingrcnnsinlimitedcomputationpowerdevices AT juanignaciovazquezgomez gesturebasedhumanmachineinteractionusingrcnnsinlimitedcomputationpowerdevices AT surajitsaikia gesturebasedhumanmachineinteractionusingrcnnsinlimitedcomputationpowerdevices |