Cargando…

An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery

For the issue of low accuracy and poor real-time performance of insulator and defect detection by an unmanned aerial vehicle (UAV) in the process of power inspection, an insulator detection model MobileNet_CenterNet was proposed in this study. First, the lightweight network MobileNet V1 was used to...

Descripción completa

Detalles Bibliográficos
Autores principales: Xia, Haiyang, Yang, Baohua, Li, Yunlong, Wang, Bing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9031845/
https://www.ncbi.nlm.nih.gov/pubmed/35458835
http://dx.doi.org/10.3390/s22082850
_version_ 1784692492516458496
author Xia, Haiyang
Yang, Baohua
Li, Yunlong
Wang, Bing
author_facet Xia, Haiyang
Yang, Baohua
Li, Yunlong
Wang, Bing
author_sort Xia, Haiyang
collection PubMed
description For the issue of low accuracy and poor real-time performance of insulator and defect detection by an unmanned aerial vehicle (UAV) in the process of power inspection, an insulator detection model MobileNet_CenterNet was proposed in this study. First, the lightweight network MobileNet V1 was used to replace the feature extraction network Resnet-50 of the original model, aiming to ensure the detection accuracy of the model while speeding up its detection speed. Second, a spatial and channel attention mechanism convolutional block attention module (CBAM) was introduced in CenterNet, aiming to improve the prediction accuracy of small target insulator position information. Then, three transposed convolution modules were added for upsampling, aiming to better restore the semantic information and position information of the image. Finally, the insulator dataset (ID) constructed by ourselves and the public dataset (CPLID) were used for model training and validation, aiming to improve the generalization ability of the model. The experimental results showed that compared with the CenterNet model, MobileNet_CenterNet improved the detection accuracy by 12.2%, the inference speed by 1.1 f/s for FPS-CPU and 4.9 f/s for FPS-GPU, and the model size was reduced by 37 MB. Compared with other models, our proposed model improved both detection accuracy and inference speed, indicating that the MobileNet_CenterNet model had better real-time performance and robustness.
format Online
Article
Text
id pubmed-9031845
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90318452022-04-23 An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery Xia, Haiyang Yang, Baohua Li, Yunlong Wang, Bing Sensors (Basel) Article For the issue of low accuracy and poor real-time performance of insulator and defect detection by an unmanned aerial vehicle (UAV) in the process of power inspection, an insulator detection model MobileNet_CenterNet was proposed in this study. First, the lightweight network MobileNet V1 was used to replace the feature extraction network Resnet-50 of the original model, aiming to ensure the detection accuracy of the model while speeding up its detection speed. Second, a spatial and channel attention mechanism convolutional block attention module (CBAM) was introduced in CenterNet, aiming to improve the prediction accuracy of small target insulator position information. Then, three transposed convolution modules were added for upsampling, aiming to better restore the semantic information and position information of the image. Finally, the insulator dataset (ID) constructed by ourselves and the public dataset (CPLID) were used for model training and validation, aiming to improve the generalization ability of the model. The experimental results showed that compared with the CenterNet model, MobileNet_CenterNet improved the detection accuracy by 12.2%, the inference speed by 1.1 f/s for FPS-CPU and 4.9 f/s for FPS-GPU, and the model size was reduced by 37 MB. Compared with other models, our proposed model improved both detection accuracy and inference speed, indicating that the MobileNet_CenterNet model had better real-time performance and robustness. MDPI 2022-04-08 /pmc/articles/PMC9031845/ /pubmed/35458835 http://dx.doi.org/10.3390/s22082850 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Xia, Haiyang
Yang, Baohua
Li, Yunlong
Wang, Bing
An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery
title An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery
title_full An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery
title_fullStr An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery
title_full_unstemmed An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery
title_short An Improved CenterNet Model for Insulator Defect Detection Using Aerial Imagery
title_sort improved centernet model for insulator defect detection using aerial imagery
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9031845/
https://www.ncbi.nlm.nih.gov/pubmed/35458835
http://dx.doi.org/10.3390/s22082850
work_keys_str_mv AT xiahaiyang animprovedcenternetmodelforinsulatordefectdetectionusingaerialimagery
AT yangbaohua animprovedcenternetmodelforinsulatordefectdetectionusingaerialimagery
AT liyunlong animprovedcenternetmodelforinsulatordefectdetectionusingaerialimagery
AT wangbing animprovedcenternetmodelforinsulatordefectdetectionusingaerialimagery
AT xiahaiyang improvedcenternetmodelforinsulatordefectdetectionusingaerialimagery
AT yangbaohua improvedcenternetmodelforinsulatordefectdetectionusingaerialimagery
AT liyunlong improvedcenternetmodelforinsulatordefectdetectionusingaerialimagery
AT wangbing improvedcenternetmodelforinsulatordefectdetectionusingaerialimagery