Automated pothole condition assessment in pavement using photogrammetry-assisted convolutional neural network

Automated detection of pavement distress can prevent deterioration of premature surface disintegration in pavements. Potholes that are a common sight in harsh and cold terrains are a severe threat to road safety and a major contributing factor to pavement distress. To facilitate timely detection and repair of potholes, a computationally light and feasible, intelligent pavement pothole detection system is proposed by developing a novel workflow for image-based detection and severity assessment. A single-stage convolutional neural network (CNN) architecture, RetinaNet is modified and optimised to best detect potholes and used in combination with a novel pothole depth estimation algorithm. A comparative evaluation of the model’s performance against the existing state-of-the-art model on the benchmark dataset establishes the proposed model’s high performance and applicability in real-time scenarios. The depth estimation algorithm is based on a 3D road surface model generated by employing the photogrammetric process of structure from motion (SfM). The point cloud data obtained thereafter, is used for accurate measurement of pothole depth. The comparison of the derived depth with the onsite depth measurement of the pothole reveals a mean error below 5%. This method leads to a practical and intelligent solution to be implemented as part of a potential pavement health assessment system for future practice.

• Record URL:
  https://doi.org/10.1080/10298436.2023.2183401
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/44544515
• Supplemental Notes:
  • © 2023 Informa UK Limited, trading as Taylor & Francis Group 2023. Abstract reprinted with permission of Taylor & Francis.
• Authors:
  • Ranyal, Eshta
  • Sadhu, Ayan
  • 0000-0001-5685-7087
  • Jain, Kamal
  • 0000-0001-5153-0405
• Publication Date: 2023-12

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 2183401
• Serial:
  • International Journal of Pavement Engineering
  • Volume: 24
  • Issue Number: 1
  • Publisher: Taylor & Francis
  • ISSN: 1029-8436
  • Serial URL: http://www.tandf.co.uk/journals/titles/10298436.html

Subject/Index Terms

• TRT Terms: Algorithms; Depth; Detection and identification; Neural networks; Photogrammetry; Potholes
• Subject Areas: Highways; Maintenance and Preservation; Pavements;

Filing Info

• Accession Number: 01906749
• Record Type: Publication
• Files: TRIS
• Created Date: Feb 2 2024 4:14PM