Weakly-supervised surface crack segmentation by generating pseudo-labels using localization with a classifier and thresholding

Jacob Konig*, Mark David Jenkins, Mike Mannion, Peter Barrie, Gordon Morison

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)
8 Downloads (Pure)

Abstract

Surface cracks are a common sight on public infrastructure nowadays. Recent work has been addressing this problem by supporting structural maintenance measures using machine learning methods. Those methods are used to segment surface cracks from their background, making them easier to localize. However, a common issue is that to create a well-functioning algorithm, the training data needs to have detailed annotations of pixels that belong to cracks. Our work proposes a weakly supervised approach that leverages a CNN classifier in a novel way to create surface crack pseudo labels. First, we use the classifier to create a rough crack localization map by using its class activation maps and a patch based classification approach and fuse this with a thresholding based approach to segment the mostly darker crack pixels. The classifier assists in suppressing noise from the background regions, which commonly are incorrectly highlighted as cracks by standard thresholding methods. Then, the pseudo labels can be used in an end-to-end approach when training a standard CNN for surface crack segmentation. Our method is shown to yield sufficiently accurate pseudo labels. Those labels, incorporated into segmentation CNN training using multiple recent crack segmentation architectures, achieve comparable performance to fully supervised methods on four popular crack segmentation datasets.
Original languageEnglish
Pages (from-to)24083-24094
Number of pages12
JournalIEEE Transactions on Intelligent Transportation Systems
Volume23
Issue number12
DOIs
Publication statusPublished - 21 Sep 2022

Keywords

  • weakly supervised learning
  • neural networks
  • Surface morphology
  • Standards
  • Deep learning
  • Location awareness
  • Training
  • Image segmentation
  • Convolutional neural networks
  • Surface cracks

ASJC Scopus subject areas

  • Mechanical Engineering
  • Automotive Engineering
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Weakly-supervised surface crack segmentation by generating pseudo-labels using localization with a classifier and thresholding'. Together they form a unique fingerprint.

Cite this