EUVIMEDEUVIMED entdecken
Crossref

Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks

Zhuo Liu, Shuo Pan, Zhiwei Gao, Ning Chen, Feng Li, Linbing Wang, Yue Hou

Automation in Construction · 2023-02 · 146 · 104674

DOI: 10.1016/j.autcon.2022.104674 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Automation in Construction, 2023-02. Verfasst von Zhuo Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 45 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

13 Automatic monitoring of pavement structure health has always been a significant problem for transportation 14 engineers. Although the generative adversarial network (GAN) has proven to be an effective tool for improving 15 pavement distress recognition accuracy, it may lead to increased computational cost, which inconsistent with the 16 requirements of engineering practice. This paper describes a lightweight GAN structure for automatic pavement 17 distress identification with high computation efficiency and low computation cost. Squeeze and expand (SE), 18 multiscale convolution (MC), and depthwise separable convolution (DSC) were selected as alternative lightweight 19 methods, and two series of comparative experiments were conducted. The results showed that the GAN-based 20 model with SE implemented on its fully connected layer, MC&DSC implemented on its transpose convolution 21 layers in the generator, and MC implemented on its convolution layers in the discriminator could reduce the 22 largest proportion of model parameters (94.8%) while achieving satisfactory classification accuracy (85.4%).

Zitieren

APA

Liu, Z., Pan, S., Gao, Z., Chen, N., Li, F., Wang, L., & Hou, Y. (2023). Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks. Automation in Construction, 146, 104674. https://doi.org/10.1016/j.autcon.2022.104674

Vancouver

Liu Z, Pan S, Gao Z, Chen N, Li F, Wang L, et al. Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks. Automation in Construction. 2023;146:104674. doi:10.1016/j.autcon.2022.104674

BibTeX
@article{Liu2023,
  author = {Liu, Zhuo and Pan, Shuo and Gao, Zhiwei and Chen, Ning and Li, Feng and Wang, Linbing and Hou, Yue},
  title = {Automatic intelligent recognition of pavement distresses with limited dataset using generative adversarial networks},
  journal = {Automation in Construction},
  year = {2023},
  volume = {146},
  pages = {104674},
  doi = {10.1016/j.autcon.2022.104674}
}
Kostenlos starten →