Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection

Autores
Santos, David O.; Montalvão, Jugurta; Araujo, Charles A. C.; Lebre, Ulisses D. E. S.; Ferreira, Tarso V.; Oliveira Freire, Eduardo
Año de publicación
2024
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola–Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates 1 scores below 26% in both spectra, while VJ’s scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms’ strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach.
Fil: Santos, David O.. Universidade Federal de Campina Grande; Brasil
Fil: Montalvão, Jugurta. Universidade Federal de Sergipe; Brasil
Fil: Araujo, Charles A. C.. Electrical Operation, Eneva S.a; Brasil
Fil: Lebre, Ulisses D. E. S.. Electrical Operation, Eneva S.a; Brasil
Fil: Ferreira, Tarso V.. Universidade Federal de Sergipe; Brasil
Fil: Oliveira Freire, Eduardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tucumán. Instituto Superior de Investigaciones Biológicas. Universidad Nacional de Tucumán. Instituto Superior de Investigaciones Biológicas; Argentina. Universidade Federal de Sergipe; Brasil
Materia
Electrical equipment
Infrared spectrum
Machine vision
Object detection
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/260572
Acceder
id CONICETDig_f82b4588796cbff6fb1cb7b70f2d44d9
oai_identifier_str oai:ri.conicet.gov.ar:11336/260572
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment DetectionSantos, David O.Montalvão, JugurtaAraujo, Charles A. C.Lebre, Ulisses D. E. S.Ferreira, Tarso V.Oliveira Freire, EduardoElectrical equipmentInfrared spectrumMachine visionObject detectionhttps://purl.org/becyt/ford/2.2https://purl.org/becyt/ford/2This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola–Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates 1 scores below 26% in both spectra, while VJ’s scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms’ strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach.Fil: Santos, David O.. Universidade Federal de Campina Grande; BrasilFil: Montalvão, Jugurta. Universidade Federal de Sergipe; BrasilFil: Araujo, Charles A. C.. Electrical Operation, Eneva S.a; BrasilFil: Lebre, Ulisses D. E. S.. Electrical Operation, Eneva S.a; BrasilFil: Ferreira, Tarso V.. Universidade Federal de Sergipe; BrasilFil: Oliveira Freire, Eduardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tucumán. Instituto Superior de Investigaciones Biológicas. Universidad Nacional de Tucumán. Instituto Superior de Investigaciones Biológicas; Argentina. Universidade Federal de Sergipe; BrasilMultidisciplinary Digital Publishing Institute2024-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/260572Santos, David O.; Montalvão, Jugurta; Araujo, Charles A. C.; Lebre, Ulisses D. E. S.; Ferreira, Tarso V.; et al.; Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection; Multidisciplinary Digital Publishing Institute; Sensors; 24; 13; 6-2024; 1-201424-8220CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/1424-8220/24/13/4219info:eu-repo/semantics/altIdentifier/doi/10.3390/s24134219info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-10-15T14:57:55Zoai:ri.conicet.gov.ar:11336/260572instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-10-15 14:57:55.855CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection
title Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection
spellingShingle Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection
Santos, David O.
Electrical equipment
Infrared spectrum
Machine vision
Object detection
title_short Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection
title_full Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection
title_fullStr Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection
title_full_unstemmed Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection
title_sort Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection
dc.creator.none.fl_str_mv Santos, David O.
Montalvão, Jugurta
Araujo, Charles A. C.
Lebre, Ulisses D. E. S.
Ferreira, Tarso V.
Oliveira Freire, Eduardo
author Santos, David O.
author_facet Santos, David O.
Montalvão, Jugurta
Araujo, Charles A. C.
Lebre, Ulisses D. E. S.
Ferreira, Tarso V.
Oliveira Freire, Eduardo
author_role author
author2 Montalvão, Jugurta
Araujo, Charles A. C.
Lebre, Ulisses D. E. S.
Ferreira, Tarso V.
Oliveira Freire, Eduardo
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Electrical equipment
Infrared spectrum
Machine vision
Object detection
topic Electrical equipment
Infrared spectrum
Machine vision
Object detection
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.2
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola–Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates 1 scores below 26% in both spectra, while VJ’s scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms’ strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach.
Fil: Santos, David O.. Universidade Federal de Campina Grande; Brasil
Fil: Montalvão, Jugurta. Universidade Federal de Sergipe; Brasil
Fil: Araujo, Charles A. C.. Electrical Operation, Eneva S.a; Brasil
Fil: Lebre, Ulisses D. E. S.. Electrical Operation, Eneva S.a; Brasil
Fil: Ferreira, Tarso V.. Universidade Federal de Sergipe; Brasil
Fil: Oliveira Freire, Eduardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tucumán. Instituto Superior de Investigaciones Biológicas. Universidad Nacional de Tucumán. Instituto Superior de Investigaciones Biológicas; Argentina. Universidade Federal de Sergipe; Brasil
description This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola–Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates 1 scores below 26% in both spectra, while VJ’s scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms’ strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach.
publishDate 2024
dc.date.none.fl_str_mv 2024-06
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/260572
Santos, David O.; Montalvão, Jugurta; Araujo, Charles A. C.; Lebre, Ulisses D. E. S.; Ferreira, Tarso V.; et al.; Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection; Multidisciplinary Digital Publishing Institute; Sensors; 24; 13; 6-2024; 1-20
1424-8220
CONICET Digital
CONICET
url http://hdl.handle.net/11336/260572
identifier_str_mv Santos, David O.; Montalvão, Jugurta; Araujo, Charles A. C.; Lebre, Ulisses D. E. S.; Ferreira, Tarso V.; et al.; Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection; Multidisciplinary Digital Publishing Institute; Sensors; 24; 13; 6-2024; 1-20
1424-8220
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/1424-8220/24/13/4219
info:eu-repo/semantics/altIdentifier/doi/10.3390/s24134219
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1846083118803451904
score 13.22299

Publicaciones similares