Automated assessment of cracks on concrete surfaces using adaptive digital image processing

Yufei Liu, Soojin Cho, Billie F. Spencer, Jiansheng Fan

Research output: Contribution to journalArticle

Abstract

Monitoring surface cracks is important to ensure the health of concrete structures. However, traditional visual inspection to monitor the concrete cracks has disadvantages such as subjective inspection nature, associated time and cost, and possible danger to inspectors. To alter the visual inspection, a complete procedure for automated crack assessment based on adaptive digital image processing has been proposed in this study. Crack objects are extracted from the images using the subtraction with median filter and the local binarization using the Niblack's method. To adaptively determine the optimal window sizes for the median filter and the Niblack's method without distortion of crack object, an optimal filter size index (OFSI) is proposed. From the extracted crack objects using the optimal size of window, the crack objects are decomposed to the crack skeletons and edges, and the crack width is calculated using 4-connected normal line according to the orientation of the local skeleton line. For an image, a crack width nephogram is obtained to have an intuitive view of the crack distribution. The proposed procedure is verified from a test on a concrete reaction wall with various types of cracks. From the crack images with different crack widths and patterns, the widths of cracks in the order of submillimeters are calculated with high accuracy.

Original languageEnglish (US)
Pages (from-to)719-741
Number of pages23
JournalSmart Structures and Systems
Volume14
Issue number4
DOIs
StatePublished - Oct 1 2014

Keywords

  • Adaptive image processing
  • Crack width
  • Digital image processing
  • Median filter
  • Window size

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Automated assessment of cracks on concrete surfaces using adaptive digital image processing'. Together they form a unique fingerprint.

Cite this