EUVIMEDEUVIMED entdecken
Open Access

Automatic pavement texture recognition using lightweight few-shot learning

Shuo Pan iD, Hai Yan iD, Zhuo Liu iD, Ning Chen, Yinghao Miao, Yue Hou iD

Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · 04.09.2023 · 381 (2254)

DOI: 10.1098/rsta.2022.0166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, online erschienen am 17.07.2023. Verfasst von Shuo Pan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, People's Republic of China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Opening Project Fund of Materials Service Safety Assessment Facilities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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'.

Schlagwörter

Stichwörter der Autor:innen

Siamese networkconvolutional neural networkdeep learningone-dimensional convolutionpavement detection

Autor:innen und Institutionen

  • Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, People's Republic of China.
  • National Center for Materials Service Safety, University of Science and Technology Beijing, Beijing 100083, People's Republic of China.
  • Department of Civil Engineering, Faculty of Science and Engineering, Swansea University, Swansea SA1 8EN, UK.

ORCID-Profile: Shuo Pan, Hai Yan, Zhuo Liu, Yue Hou

Förderung

  • Opening Project Fund of Materials Service Safety Assessment Facilities

Zitieren

APA

Pan, S., Yan, H., Liu, Z., Chen, N., Miao, Y., & Hou, Y. (2023). Automatic pavement texture recognition using lightweight few-shot learning. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 381(2254). https://doi.org/10.1098/rsta.2022.0166

Vancouver

Pan S, Yan H, Liu Z, Chen N, Miao Y, Hou Y. Automatic pavement texture recognition using lightweight few-shot learning. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2023;381(2254). doi:10.1098/rsta.2022.0166

BibTeX
@article{Pan2023,
  author = {Pan, Shuo and Yan, Hai and Liu, Zhuo and Chen, Ning and Miao, Yinghao and Hou, Yue},
  title = {Automatic pavement texture recognition using lightweight few-shot learning},
  journal = {Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences},
  year = {2023},
  volume = {381},
  number = {2254},
  doi = {10.1098/rsta.2022.0166}
}
Kostenlos starten →