Cargando…

An annotated water-filled, and dry potholes dataset for deep learning applications

Potholes have long posed a challenging risk to automated systems due to their random and stochastic shapes and the reflectiveness of their surface when filled with water, whether it is “muddy” water or clear water. This has formed a significant limitation to autonomous assistive technologies such as...

Descripción completa

Detalles Bibliográficos
Autores principales: Dib, Jihad, Sirlantzis, Konstantinos, Howells, Gareth
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10197008/
https://www.ncbi.nlm.nih.gov/pubmed/37213553
http://dx.doi.org/10.1016/j.dib.2023.109206
_version_ 1785044461733019648
author Dib, Jihad
Sirlantzis, Konstantinos
Howells, Gareth
author_facet Dib, Jihad
Sirlantzis, Konstantinos
Howells, Gareth
author_sort Dib, Jihad
collection PubMed
description Potholes have long posed a challenging risk to automated systems due to their random and stochastic shapes and the reflectiveness of their surface when filled with water, whether it is “muddy” water or clear water. This has formed a significant limitation to autonomous assistive technologies such as Electric-Powered Wheelchairs (EPWs), mobility scooters, etc. due to the risk potholes pose on the user's well-being as it could cause severe falls and injuries as well as neck and back problems. Current research proved that Deep Leaning technologies are one of the most relevant solutions used to detect potholes due to the high accuracy of the detection. One of the main limitations to the datasets currently made available is the lack of photos describing water-filled, rabble-filled, and random coloured potholes. The purpose of our dataset is to provide the answer to this problem as it contains 713 high-quality photos representing 1152 manuall-annotated potholes in different shapes, locations, colours, and conditions, all of which were manually-collected via a mobile phone and within different areas in the United Kingdom along with two additional benchmarking videos recorded via a dashcam.
format Online
Article
Text
id pubmed-10197008
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-101970082023-05-20 An annotated water-filled, and dry potholes dataset for deep learning applications Dib, Jihad Sirlantzis, Konstantinos Howells, Gareth Data Brief Data Article Potholes have long posed a challenging risk to automated systems due to their random and stochastic shapes and the reflectiveness of their surface when filled with water, whether it is “muddy” water or clear water. This has formed a significant limitation to autonomous assistive technologies such as Electric-Powered Wheelchairs (EPWs), mobility scooters, etc. due to the risk potholes pose on the user's well-being as it could cause severe falls and injuries as well as neck and back problems. Current research proved that Deep Leaning technologies are one of the most relevant solutions used to detect potholes due to the high accuracy of the detection. One of the main limitations to the datasets currently made available is the lack of photos describing water-filled, rabble-filled, and random coloured potholes. The purpose of our dataset is to provide the answer to this problem as it contains 713 high-quality photos representing 1152 manuall-annotated potholes in different shapes, locations, colours, and conditions, all of which were manually-collected via a mobile phone and within different areas in the United Kingdom along with two additional benchmarking videos recorded via a dashcam. Elsevier 2023-05-06 /pmc/articles/PMC10197008/ /pubmed/37213553 http://dx.doi.org/10.1016/j.dib.2023.109206 Text en © 2023 Published by Elsevier Inc. https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Data Article
Dib, Jihad
Sirlantzis, Konstantinos
Howells, Gareth
An annotated water-filled, and dry potholes dataset for deep learning applications
title An annotated water-filled, and dry potholes dataset for deep learning applications
title_full An annotated water-filled, and dry potholes dataset for deep learning applications
title_fullStr An annotated water-filled, and dry potholes dataset for deep learning applications
title_full_unstemmed An annotated water-filled, and dry potholes dataset for deep learning applications
title_short An annotated water-filled, and dry potholes dataset for deep learning applications
title_sort annotated water-filled, and dry potholes dataset for deep learning applications
topic Data Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10197008/
https://www.ncbi.nlm.nih.gov/pubmed/37213553
http://dx.doi.org/10.1016/j.dib.2023.109206
work_keys_str_mv AT dibjihad anannotatedwaterfilledanddrypotholesdatasetfordeeplearningapplications
AT sirlantziskonstantinos anannotatedwaterfilledanddrypotholesdatasetfordeeplearningapplications
AT howellsgareth anannotatedwaterfilledanddrypotholesdatasetfordeeplearningapplications
AT dibjihad annotatedwaterfilledanddrypotholesdatasetfordeeplearningapplications
AT sirlantziskonstantinos annotatedwaterfilledanddrypotholesdatasetfordeeplearningapplications
AT howellsgareth annotatedwaterfilledanddrypotholesdatasetfordeeplearningapplications