Interfaces gestuais baseados no controlador Leap Motion
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.26/36452 |
Resumo: | In the present, most of the human-machine interactions are based on the use of peripherals such as keyboard and computer mouse. However, the use of such peripherals can create certain limitations in the way people interact with machines, for this reason, there is a need to create natural interfaces. One of the possible approaches that has been proposed involves performing gestures that are recognized by a sensor and interpreted by the computer. The use of hands on a human-machine interface is justified by the fact that the hands are an important element in nonverbal communications. Due to this, in this project several possible gesture interfaces were analyzed, using the Leap Motion sensor. The project was based on the development of methods that allowed the recognition of gestures and their association to an action that the computer should perform. Through the analysis of existing studies in the area and the various methods used to allow a program to classify a data set, a gesture classification system was developed. The classification system has tested to verify its accuracy and precision. Using the knowledge obtained throughout the project, and as proof of concept, an application was developed to demonstrate the usefulness of the classification system in a real situation. This application can recognize a gesture and associate it with a keyboard key, allowing a user to write the message resulting from the gestures he makes. This project main conclusion was that the gesture classification system trained using SVM can make a good separation of the various gestures and with this classify correctly the gestures. Most of problems that arise during the recognition of a gesture are a consequence of the Leap Motion not being able to track correctly the gesture being made. |
id |
RCAP_f2a2a25afece8e4ee74e336e5e1b1e5a |
---|---|
oai_identifier_str |
oai:comum.rcaap.pt:10400.26/36452 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Interfaces gestuais baseados no controlador Leap MotionLeap motionHand gestureGesture interfacesGesture classificationClassification systemMotion sensorIn the present, most of the human-machine interactions are based on the use of peripherals such as keyboard and computer mouse. However, the use of such peripherals can create certain limitations in the way people interact with machines, for this reason, there is a need to create natural interfaces. One of the possible approaches that has been proposed involves performing gestures that are recognized by a sensor and interpreted by the computer. The use of hands on a human-machine interface is justified by the fact that the hands are an important element in nonverbal communications. Due to this, in this project several possible gesture interfaces were analyzed, using the Leap Motion sensor. The project was based on the development of methods that allowed the recognition of gestures and their association to an action that the computer should perform. Through the analysis of existing studies in the area and the various methods used to allow a program to classify a data set, a gesture classification system was developed. The classification system has tested to verify its accuracy and precision. Using the knowledge obtained throughout the project, and as proof of concept, an application was developed to demonstrate the usefulness of the classification system in a real situation. This application can recognize a gesture and associate it with a keyboard key, allowing a user to write the message resulting from the gestures he makes. This project main conclusion was that the gesture classification system trained using SVM can make a good separation of the various gestures and with this classify correctly the gestures. Most of problems that arise during the recognition of a gesture are a consequence of the Leap Motion not being able to track correctly the gesture being made.Martins, Nuno Alexandre CidParedes, Simão Pedro Mendes Cruz ReisRepositório ComumBizarro, João Pedro Pereira2021-05-10T11:12:18Z2018-12-132019-06-24T00:00:00Z2019-06-24T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.26/36452porinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2022-09-05T15:41:03Zoai:comum.rcaap.pt:10400.26/36452Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T15:16:51.000622Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Interfaces gestuais baseados no controlador Leap Motion |
title |
Interfaces gestuais baseados no controlador Leap Motion |
spellingShingle |
Interfaces gestuais baseados no controlador Leap Motion Bizarro, João Pedro Pereira Leap motion Hand gesture Gesture interfaces Gesture classification Classification system Motion sensor |
title_short |
Interfaces gestuais baseados no controlador Leap Motion |
title_full |
Interfaces gestuais baseados no controlador Leap Motion |
title_fullStr |
Interfaces gestuais baseados no controlador Leap Motion |
title_full_unstemmed |
Interfaces gestuais baseados no controlador Leap Motion |
title_sort |
Interfaces gestuais baseados no controlador Leap Motion |
author |
Bizarro, João Pedro Pereira |
author_facet |
Bizarro, João Pedro Pereira |
author_role |
author |
dc.contributor.none.fl_str_mv |
Martins, Nuno Alexandre Cid Paredes, Simão Pedro Mendes Cruz Reis Repositório Comum |
dc.contributor.author.fl_str_mv |
Bizarro, João Pedro Pereira |
dc.subject.por.fl_str_mv |
Leap motion Hand gesture Gesture interfaces Gesture classification Classification system Motion sensor |
topic |
Leap motion Hand gesture Gesture interfaces Gesture classification Classification system Motion sensor |
description |
In the present, most of the human-machine interactions are based on the use of peripherals such as keyboard and computer mouse. However, the use of such peripherals can create certain limitations in the way people interact with machines, for this reason, there is a need to create natural interfaces. One of the possible approaches that has been proposed involves performing gestures that are recognized by a sensor and interpreted by the computer. The use of hands on a human-machine interface is justified by the fact that the hands are an important element in nonverbal communications. Due to this, in this project several possible gesture interfaces were analyzed, using the Leap Motion sensor. The project was based on the development of methods that allowed the recognition of gestures and their association to an action that the computer should perform. Through the analysis of existing studies in the area and the various methods used to allow a program to classify a data set, a gesture classification system was developed. The classification system has tested to verify its accuracy and precision. Using the knowledge obtained throughout the project, and as proof of concept, an application was developed to demonstrate the usefulness of the classification system in a real situation. This application can recognize a gesture and associate it with a keyboard key, allowing a user to write the message resulting from the gestures he makes. This project main conclusion was that the gesture classification system trained using SVM can make a good separation of the various gestures and with this classify correctly the gestures. Most of problems that arise during the recognition of a gesture are a consequence of the Leap Motion not being able to track correctly the gesture being made. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-13 2019-06-24T00:00:00Z 2019-06-24T00:00:00Z 2021-05-10T11:12:18Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.26/36452 |
url |
http://hdl.handle.net/10400.26/36452 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799130031292678144 |