A computer vision-based crack quantification of reinforced concrete shells using graph theory measures

Pedram Bazrafshan; Thinh On; Arvin Ebrahimkhanlou

doi:10.1117/12.2612359

18 April 2022 A computer vision-based crack quantification of reinforced concrete shells using graph theory measures

Pedram Bazrafshan, Thinh On, Arvin Ebrahimkhanlou

Author Affiliations +

Proceedings Volume 12046, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2022; 120460J (2022) https://doi.org/10.1117/12.2612359
Event: SPIE Smart Structures + Nondestructive Evaluation, 2022, Long Beach, California, United States

Abstract

SHM and NDE/NDT are developed to evaluate the amount of damage to a structure. Since human inspections are prone to misdiagnosis and/or miss-interpretations, the damage assessment and identification methods are shifting from human-based to computer-based. In this article, a computer vision method is used to detect and quantify the cracks on a concrete surface. After processing the crack images, cracks are modeled as graphs for feature extraction. To study the proposed method, concrete surface crack images from a reinforced concrete shell under quasi-linear load at each load step are used. Pearson correlation analysis is implemented to evaluate the relationship between graph measures at the north and south faces of the wall. All correlation values are above 50%, and eight out of ten graph measures demonstrated a correlation above 85%. The average correlation value between both sides of the wall reports 84% compatibility. High correlation values between the two sides of the wall attribute to the fidelity of graph features to the crack patterns on the two sides of the wall. Moreover, the monotonic increases in different graph measures and damage indexes indicate that the extracted features from the converted crack patterns to graph are meaningful information. Results of this study reveal that the proposed crack quantification method has the potential of translating crack patterns for further machine learning applications. This novel idea of using different graph measures introduces more features and can act as a base to study the fundamental and mathematical relation between crack patterns and graph theory.

Conference Presentation

Citation Download Citation

Pedram Bazrafshan, Thinh On, and Arvin Ebrahimkhanlou "A computer vision-based crack quantification of reinforced concrete shells using graph theory measures", Proc. SPIE 12046, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2022, 120460J (18 April 2022); https://doi.org/10.1117/12.2612359

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE