Cargando…

Automatic pavement texture recognition using lightweight few-shot learning

Texture is a crucial characteristic of roads, closely related to their performance. The recognition of pavement texture is of great significance for road maintenance professionals to detect potential safety hazards and carry out necessary countermeasures. Although deep learning models have been appl...

Descripción completa

Detalles Bibliográficos
Autores principales: Pan, Shuo, Yan, Hai, Liu, Zhuo, Chen, Ning, Miao, Yinghao, Hou, Yue
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10350336/
https://www.ncbi.nlm.nih.gov/pubmed/37454689
http://dx.doi.org/10.1098/rsta.2022.0166
_version_ 1785074113343127552
author Pan, Shuo
Yan, Hai
Liu, Zhuo
Chen, Ning
Miao, Yinghao
Hou, Yue
author_facet Pan, Shuo
Yan, Hai
Liu, Zhuo
Chen, Ning
Miao, Yinghao
Hou, Yue
author_sort Pan, Shuo
collection PubMed
description Texture is a crucial characteristic of roads, closely related to their performance. The recognition of pavement texture is of great significance for road maintenance professionals to detect potential safety hazards and carry out necessary countermeasures. Although deep learning models have been applied for recognition, the scarcity of data has always been a limitation. To address this issue, this paper proposes a few-shot learning model based on the Siamese network for pavement texture recognition with a limited dataset. The model achieved 89.8% accuracy in a four-way five-shot task classifying the pavement textures of dense asphalt concrete, micro surface, open-graded friction course and stone matrix asphalt. To align with engineering practice, global average pooling (GAP) and one-dimensional convolution are implemented, creating lightweight models that save storage and training time. Comparative experiments show that the lightweight model with GAP implemented on dense layers and one-dimensional convolution on convolutional layers reduced storage volume by 94% and training time by 99%, despite a 2.9% decrease in classification accuracy. Moreover, the model with only GAP implemented on dense layers achieved the highest accuracy at 93.5%, while reducing storage volume and training time by 83% and 6%, respectively. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.
format Online
Article
Text
id pubmed-10350336
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher The Royal Society
record_format MEDLINE/PubMed
spelling pubmed-103503362023-07-17 Automatic pavement texture recognition using lightweight few-shot learning Pan, Shuo Yan, Hai Liu, Zhuo Chen, Ning Miao, Yinghao Hou, Yue Philos Trans A Math Phys Eng Sci Articles Texture is a crucial characteristic of roads, closely related to their performance. The recognition of pavement texture is of great significance for road maintenance professionals to detect potential safety hazards and carry out necessary countermeasures. Although deep learning models have been applied for recognition, the scarcity of data has always been a limitation. To address this issue, this paper proposes a few-shot learning model based on the Siamese network for pavement texture recognition with a limited dataset. The model achieved 89.8% accuracy in a four-way five-shot task classifying the pavement textures of dense asphalt concrete, micro surface, open-graded friction course and stone matrix asphalt. To align with engineering practice, global average pooling (GAP) and one-dimensional convolution are implemented, creating lightweight models that save storage and training time. Comparative experiments show that the lightweight model with GAP implemented on dense layers and one-dimensional convolution on convolutional layers reduced storage volume by 94% and training time by 99%, despite a 2.9% decrease in classification accuracy. Moreover, the model with only GAP implemented on dense layers achieved the highest accuracy at 93.5%, while reducing storage volume and training time by 83% and 6%, respectively. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'. The Royal Society 2023-09-04 2023-07-17 /pmc/articles/PMC10350336/ /pubmed/37454689 http://dx.doi.org/10.1098/rsta.2022.0166 Text en © 2023 The Authors. https://creativecommons.org/licenses/by/4.0/Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, provided the original author and source are credited.
spellingShingle Articles
Pan, Shuo
Yan, Hai
Liu, Zhuo
Chen, Ning
Miao, Yinghao
Hou, Yue
Automatic pavement texture recognition using lightweight few-shot learning
title Automatic pavement texture recognition using lightweight few-shot learning
title_full Automatic pavement texture recognition using lightweight few-shot learning
title_fullStr Automatic pavement texture recognition using lightweight few-shot learning
title_full_unstemmed Automatic pavement texture recognition using lightweight few-shot learning
title_short Automatic pavement texture recognition using lightweight few-shot learning
title_sort automatic pavement texture recognition using lightweight few-shot learning
topic Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10350336/
https://www.ncbi.nlm.nih.gov/pubmed/37454689
http://dx.doi.org/10.1098/rsta.2022.0166
work_keys_str_mv AT panshuo automaticpavementtexturerecognitionusinglightweightfewshotlearning
AT yanhai automaticpavementtexturerecognitionusinglightweightfewshotlearning
AT liuzhuo automaticpavementtexturerecognitionusinglightweightfewshotlearning
AT chenning automaticpavementtexturerecognitionusinglightweightfewshotlearning
AT miaoyinghao automaticpavementtexturerecognitionusinglightweightfewshotlearning
AT houyue automaticpavementtexturerecognitionusinglightweightfewshotlearning