Cargando…

Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection

Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to t...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Dongping, Yu, Xuecheng, Yang, Li, Quan, Daying, Mi, Hongmei, Yan, Ke
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007452/
https://www.ncbi.nlm.nih.gov/pubmed/36904880
http://dx.doi.org/10.3390/s23052676
_version_ 1784905525038678016
author Zhang, Dongping
Yu, Xuecheng
Yang, Li
Quan, Daying
Mi, Hongmei
Yan, Ke
author_facet Zhang, Dongping
Yu, Xuecheng
Yang, Li
Quan, Daying
Mi, Hongmei
Yan, Ke
author_sort Zhang, Dongping
collection PubMed
description Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model.
format Online
Article
Text
id pubmed-10007452
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100074522023-03-12 Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection Zhang, Dongping Yu, Xuecheng Yang, Li Quan, Daying Mi, Hongmei Yan, Ke Sensors (Basel) Article Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model. MDPI 2023-03-01 /pmc/articles/PMC10007452/ /pubmed/36904880 http://dx.doi.org/10.3390/s23052676 Text en © 2023 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
Zhang, Dongping
Yu, Xuecheng
Yang, Li
Quan, Daying
Mi, Hongmei
Yan, Ke
Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection
title Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection
title_full Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection
title_fullStr Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection
title_full_unstemmed Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection
title_short Data-Augmented Deep Learning Models for Abnormal Road Manhole Cover Detection
title_sort data-augmented deep learning models for abnormal road manhole cover detection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007452/
https://www.ncbi.nlm.nih.gov/pubmed/36904880
http://dx.doi.org/10.3390/s23052676
work_keys_str_mv AT zhangdongping dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection
AT yuxuecheng dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection
AT yangli dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection
AT quandaying dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection
AT mihongmei dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection
AT yanke dataaugmenteddeeplearningmodelsforabnormalroadmanholecoverdetection