Building cracks identification by employing image segmentation

Yishuo Huang; Qain-Ying Yang; Keng-Tsang Hsu; Chih-Hung Chiang

doi:10.1117/12.2558335

22 April 2020 Building cracks identification by employing image segmentation

Yishuo Huang, Qain-Ying Yang, Keng-Tsang Hsu, Chih-Hung Chiang

Proceedings Volume 11381, Health Monitoring of Structural and Biological Systems XIV; 113811Y (2020) https://doi.org/10.1117/12.2558335
Event: SPIE Smart Structures + Nondestructive Evaluation, 2020, Online Only

Abstract

Cracks do exist in a concrete building, and the reasons for cracks can be attributed to grouting, force actions, and concrete properties. Detecting existing cracks and monitoring their growth conditions is an important issue in structure health monitoring. This study proposed an integrated approach to fuse the thermal infrared images, high-resolution image, and acoustic tracking. Thermal infrared images can be used to record the surface temperatures. Those defect areas usually have their surface temperatures different from their neighborhoods. Those surface temperature differences can be an important clue to identify the defects. From the high-resolution images, cracks do occur at those discontinuities, and those discontinuities can be treated as the boundaries of the segmented regions. In this study, an approach based on considering the distributions of the segmented regions to segment the given high-resolution images to locate the boundaries of the segmented regions. Then, the defect map is generated by overlaying the thermal infrared image on the segmented regions such that the map can reveal the defect locations, and the surface temperatures can be another evidence to show the defects. Acoustic tracking is introduced to verify the results. All the defect information is stored in a 3D model such that a defect model can be established.

Conference Presentation

Citation Download Citation

Yishuo Huang, Qain-Ying Yang, Keng-Tsang Hsu, and Chih-Hung Chiang "Building cracks identification by employing image segmentation", Proc. SPIE 11381, Health Monitoring of Structural and Biological Systems XIV, 113811Y (22 April 2020); https://doi.org/10.1117/12.2558335

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

Includes PDF, HTML & Video, when available