EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Metric Learning-Based Classification for Pavement Distress Images

Yuhui Li iD, Jiaqi Wang, Bo Lü, Hang Yang iD, Xiaotian Wu iD

Sensors · 30.06.2025 · 25 (13) · 4087

DOI: 10.3390/s25134087 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.06.2025. Verfasst von Yuhui Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Physics, Northeast Normal University, Changchun 130024, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Changchun Higher Education Institutions Pilot Project Selection Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes a deep metric learning-based pavement distress classification method to address critical limitations in conventional approaches, including their dependency on large training datasets and inability to incrementally learn new categories. To resolve high intra-class variance and low inter-class distinction in distress images, we design a CNN head with multi-cluster centroins trained via SoftTriple loss, simultaneously maximizing inter-class separation while establishing multiple intra-class centers. An adaptive weighting strategy combining sample similarity and class priors mitigates data imbalance, while soft-label techniques reduce labeling noise by evaluating similarity against support-set exemplars. Evaluations on the UAV-PDD2023 dataset demonstrate superior performance—3.2% higher macro-recall than supervised learning, and 6.7%/8.5% improvements in macro-F1/weighted-F1 over iCaRL incremental learning—validating the method’s effectiveness for real-world road inspection scenarios with evolving distress types and limited annotation.

Schlagwörter

Stichwörter der Autor:innen

SoftTriple lossdeep metric learningimage classificationpavement distress detectionsimilarity metric

Autor:innen und Institutionen

  • School of Physics, Northeast Normal University, Changchun 130024, China.
  • Liaoning Water Conservancy and Hydropower Survey, Design and Research Institute Co., Ltd., Liaoning 110000, China.
  • Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China.

ORCID-Profile: Yuhui Li, Hang Yang, Xiaotian Wu

Förderung

  • Changchun Higher Education Institutions Pilot Project Selection Program

Zitieren

APA

Li, Y., Wang, J., Lü, B., Yang, H., & Wu, X. (2025). Deep Metric Learning-Based Classification for Pavement Distress Images. Sensors, 25(13), 4087. https://doi.org/10.3390/s25134087

Vancouver

Li Y, Wang J, Lü B, Yang H, Wu X. Deep Metric Learning-Based Classification for Pavement Distress Images. Sensors. 2025;25(13):4087. doi:10.3390/s25134087

BibTeX
@article{Li2025,
  author = {Li, Yuhui and Wang, Jiaqi and Lü, Bo and Yang, Hang and Wu, Xiaotian},
  title = {Deep Metric Learning-Based Classification for Pavement Distress Images},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {4087},
  doi = {10.3390/s25134087}
}
Kostenlos starten →