Intelligent Detection of Road Cracks Based on Improved YOLOv5

Authors

  • Zhiyan Zhou Harbin University of Science and Technology
  • Xiaoyu Yu Zhongshan Institute
  • Yuji Iwahori Chubu University
  • Qing Wu Harbin University of Science and Technology
  • Haibin Wu Harbin University of Science and Technology https://orcid.org/0000-0002-2453-3691
  • Aili Wang Harbin University of Science and Technology

DOI:

https://doi.org/10.14464/ess.v10i7.599

Abstract

With the gradual increase of highway coverage, the frequency of road cracks also increases, which brings a series of security risks. It is necessary to detect road cracks, but the traditional detection method is inefficient and unsafe. In this paper, deep learning is used to detect road cracks, and an improved model BiTrans-YOLOv5 is proposed. We add Swin Transformer to YOLOv5s to replace the original C3 module, and explore the performance of Transformer in the field of road crack detection. We also change the original PANet of YOLOv5s into a bidirectional feature pyramid network (BIFPN), which can detect small targets more accurately. Experiments on the data set Road Damage show that BiTrans-YOLOv5 has improved in Precision, Recall, F1 score and mAP@0.5 compared with YOLOv5s, among which mAP@0.5 has improved by 5.4%. It is proved that BiTrans-YOLOv5 has better performance in road detection projects.

Author Biographies

Zhiyan Zhou, Harbin University of Science and Technology

Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application

Xiaoyu Yu, Zhongshan Institute

College of Electron and Information, University of Electronic Science and Technology of China

Yuji Iwahori, Chubu University

Department of Computer Science

Qing Wu, Harbin University of Science and Technology

Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application

Aili Wang, Harbin University of Science and Technology

Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application

ISCSET 2023

Downloads

Published

2023-07-16