Learning to detect cracks on damaged concrete surfaces using two-branched convolutional neural network

Jieun Lee, Hee Sun Kim, Nayoung Kim, Eun Mi Ryu, Je Won Kang

Research output: Contribution to journalArticlepeer-review

9 Scopus citations

Abstract

Image sensors are widely used for detecting cracks on concrete surfaces to help proactive and timely management of concrete structures. However, it is a challenging task to reliably detect cracks on damaged surfaces in the real world due to noise and undesired artifacts. In this paper, we propose an autonomous crack detection algorithm based on convolutional neural network (CNN) to solve the problem. To this aim, the proposed algorithm uses a two-branched CNN architecture, consisting of sub-networks named a crack-component-aware (CCA) network and a crack-region-aware (CRA) network. The CCA network is to learn gradient component regarding cracks, and the CRA network is to learn a region-of-interest by distinguishing critical cracks and noise such as scratches. Specifically, the two sub-networks are built on convolution-deconvolution CNN architectures, but also they are comprised of different functional components to achieve their own goals efficiently. The two sub-networks are trained in an end-to-end to jointly optimize parameters and produce the final output of localizing important cracks. Various crack image samples and learning methods are used for efficiently training the proposed network. In the experimental results, the proposed algorithm provides better performance in the crack detection than the conventional algorithms.

Original languageEnglish
Article number4796
JournalSensors (Switzerland)
Volume19
Issue number21
DOIs
StatePublished - 1 Nov 2019

Keywords

  • Convolutional neural network
  • Crack detection
  • Deep learning
  • Edge detection
  • Fire-damaged concrete
  • Image processing

Fingerprint

Dive into the research topics of 'Learning to detect cracks on damaged concrete surfaces using two-branched convolutional neural network'. Together they form a unique fingerprint.

Cite this