Skip to main content

Research Repository

Advanced Search

Novel visual crack width measurement based on backbone double-scale features for improved detection automation

Tang, Yunchao; Huang, Zhaofeng; Chen, Zhang; Chen, Mingyou; Zhou, Hao; Zhang, Hexin; Sun, Junbo


Yunchao Tang

Zhaofeng Huang

Zhang Chen

Mingyou Chen

Hao Zhou

Junbo Sun


State-of-the-art machine-vision systems have limitations associated with crack width measurements. The sample points used to describe the crack width are often subjectively defined by experimenters, which obscures the crack width ground truth. Consequently, in most related studies, the uncontrollable system errors of vision modules result in unsatisfactory measurement accuracy. In this study, the cracks of a reservoir dam are taken as objects, and a new crack backbone refinement algorithm and width-measurement scheme are proposed. The algorithm simplifies the redundant data in the crack image and improves the efficiency of crack-shape estimation. Further,
an effective definition of crack width is proposed that combines the macroscale and microscale characteristics of the backbone to obtain accurate and objective sample points for width description. Compared with classic methods, the average simplification rate of the crack backbone and the average error rate of direction judgment are all improved. The results of a series of experiments validate the efficacy of the proposed method by showing that it can improve detection automation and has potential engineering application.

Journal Article Type Article
Acceptance Date Oct 19, 2022
Online Publication Date Oct 27, 2022
Publication Date 2023-01
Deposit Date Oct 28, 2022
Publicly Available Date Oct 28, 2023
Print ISSN 0141-0296
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 274
Article Number 115158
Keywords Concrete crack, Image thinning, Machine vision, Multi-scale feature fusion
Public URL


Novel Crack-width Visual Measurement Based On Backbone Double-scale Features For Improved Detection Automation (accepted version) (7 Mb)

You might also like

Downloadable Citations