Segment-to-track for pavement crack with light-weight neural network on unmanned wheeled robot

Instance segmentation of pavement crack presents notable challenges but is pivotal for practical applications such as crack visual tracking and automated crack repair. However, slender cracks are plagued by class imbalance, low tolerance for interference in unstructured road scenes, and the presence of topological features. In this article, a novel approach called S2TNet is proposed, which enhances the contrast between the crack image foreground and background using local contrast enhancement. Specifically, the proposed anchor ratio IoU-Balanced Sampling (ARIS) and Balanced Fine-Grained Features (BFGF) effectively improve the performance of the detector in predicting bounding box and segmenting instance binary mask. Moreover, the authors establish a framework using an unmanned wheeled robot with a four-wheel independent differential drive system to deploy the S2TNet approach. Extensive experiments conducted on self-created (S2T-Crack) datasets present the effectiveness of the proposed method in achieving real-time segment-to-track at a speed of 0.05 m/s, with a segmentation precision of 80.21% for pavement cracks.

• Record URL:
  • https://doi.org/10.1016/j.autcon.2024.105346
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S0926580524000827
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/09265805
• Supplemental Notes:
  • © 2024 Published by Elsevier B.V. Abstract reprinted with permission of Elsevier.
• Authors:
  • Zhang, Jianqi
  • 0009-0001-4734-3233
  • Yang, Xu
  • Wang, Wei
  • Brilakis, Ioannis
  • 0000-0003-1829-2083
  • Davletshina, Diana
  • 0000-0003-1745-2612
  • Wang, Hainian
  • Cao, Min
• Publication Date: 2024-5

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 105346
• Serial:
  • Automation in Construction
  • Volume: 161
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0926-5805
  • Serial URL: http://www.sciencedirect.com/science/journal/09265805

Subject/Index Terms

• TRT Terms: Neural networks; Pavement cracking; Pavement maintenance; Robots
• Subject Areas: Highways; Maintenance and Preservation; Pavements;

Filing Info

• Accession Number: 01913991
• Record Type: Publication
• Files: TRIS
• Created Date: Apr 5 2024 9:03AM