EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LTPLN: Automatic pavement distress detection

Wen-Qing Huang, Liu Feng iD, Yuan-Lie He

PLOS ONE · 10.10.2024 · 19 (10) · e0309172

DOI: 10.1371/journal.pone.0309172 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 10.10.2024. Verfasst von Wen-Qing Huang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong ChengTech Tranffic&Technology Development Co., Ltd, Guangzhou, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research on Clustering Analysis of Heterogeneous Characteristics Data in Dynamic Environments.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic pavement disease detection aims to address the inefficiency in practical detection. However, traditional methods heavily rely on low-level image analysis, handcrafted features, and classical classifiers, leading to limited effectiveness and poor generalization in complex scenarios. Although significant progress has been made with deep learning methods, challenges persist in handling high-resolution images and diverse disease types. Therefore, this paper proposes a novel approach based on the lightweight Transformer Patch Labeling Network (LTPLN) to enhance the efficiency of automatic pavement disease detection and overcome the limitations of existing methods. Firstly, the input images undergo histogram equalization preprocessing to enhance image quality. Subsequently, the images are evenly partitioned into small patch blocks, serving as inputs to the enhanced Transformer model. This enhancement strategy involves integrating feature map labels at each layer of the model to reduce computational complexity and enhance model lightweightness. Furthermore, a depthwise separable convolution module is introduced into the Transformer architecture to introduce convolutional bias and reduce the model’s dependence on large amounts of data. Finally, an iterative training process utilizing the label distillation strategy based on expectation maximization is employed to update the labels of patch blocks and roughly locate the positions of pavement diseases under weak supervision. Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. These findings highlight the significant performance advantages of the LTPLN model in automatic pavement disease detection tasks, making it more efficiently applicable in real-world scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedHumansAlgorithmsNeural Networks, ComputerDeep Learning

Autor:innen und Institutionen

  • Guangdong ChengTech Tranffic&Technology Development Co., Ltd, Guangzhou, China.
  • Guangzhou Road Research Institute Co., Ltd, Guangzhou, China.
  • School of Computers, Guangdong University of Technology, Guangzhou, China.

ORCID-Profile: Liu Feng

Förderung

  • Research on Clustering Analysis of Heterogeneous Characteristics Data in Dynamic Environments

Zitieren

APA

Huang, W. Q., Feng, L., & He, Y. L. (2024). LTPLN: Automatic pavement distress detection. PLOS ONE, 19(10), e0309172. https://doi.org/10.1371/journal.pone.0309172

Vancouver

Huang WQ, Feng L, He YL. LTPLN: Automatic pavement distress detection. PLOS ONE. 2024;19(10):e0309172. doi:10.1371/journal.pone.0309172

BibTeX
@article{Huang2024,
  author = {Huang, Wen-Qing and Feng, Liu and He, Yuan-Lie},
  title = {LTPLN: Automatic pavement distress detection},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {10},
  pages = {e0309172},
  doi = {10.1371/journal.pone.0309172}
}
Kostenlos starten →