Combining block-based and pixel-based approaches to improve crack detection and localisation

Automation in Construction, vol. 122, pp. 103492

Abstract

A variety of civil engineering applications require the identification of cracks in roads and buildings. In such cases, it is frequently helpful for the precise location of cracks to be identified as labelled parts within an image to facilitate precision repair for example. CrackIT is known as a crack detection algorithm that allows a user to choose between a block-based or a pixel-based approach. The block-based approach is noise-tolerant but is not accurate in edge localization while the pixel-based approach gives accurate edge localisation but is not noise-tolerant. We propose a new approach that combines both techniques and retains the advantages of each. The new method is evaluated on three standard crack image datasets. The method was compared with the CrackIT method and three deep learning methods namely, HED, RCF and the FPHB. The new approach outperformed the existing arts and reduced the discretisation errors significantly while still being noise-tolerant.

Authors 4

1. Mohamed Abdellatif corresponding

   University of Leeds

   Affiliation as printed

   School of Civil Engineering, University of Leeds, Woodhouse lane, LS2 9JT Leeds, UK

   School of Computing, University of Leeds, Woodhouse lane, LS2 9JT Leeds, UK

2. Harriet Peel

   University of Leeds

   Affiliation as printed

   School of Civil Engineering, University of Leeds, Woodhouse lane, LS2 9JT Leeds, UK

3. Anthony G. Cohn

   Tongji University · University of Leeds · Qingdao University of Science and Technology · Shandong University

   Affiliation as printed

   Department of Computer Science and Technology, Tongji University, Shanghai 211985. China

   Luzhong Institute of Safety, Environmental Protection Engineering and Materials, Qingdao University of Science & Technology, Zibo 255000, China

   School of Civil Engineering, Shandong University, Jinan 250061, China

   School of Computing, University of Leeds, Woodhouse lane, LS2 9JT Leeds, UK

   School of Mechanical and Electrical Engineering, Qingdao University of Science and Technology, Qingdao 260061, China

4. Raúl Fuentes Aachen Institute of Geotechnical Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute of Geotechnical Engineering, RWTH Aachen University, Mies-van-der-Rohe-Straße 1, D52074 Aachen, Germany