Paper
1 April 2015 Artificial intelligence and signal processing for infrastructure assessment
Khaled Assaleh, Tamer Shanableh, Sherif Yehia
Author Affiliations +
Abstract
The Ground Penetrating Radar (GPR) is being recognized as an effective nondestructive evaluation technique to improve the inspection process. However, data interpretation and complexity of the results impose some limitations on the practicality of using this technique. This is mainly due to the need of a trained experienced person to interpret images obtained by the GPR system. In this paper, an algorithm to classify and assess the condition of infrastructures utilizing image processing and pattern recognition techniques is discussed. Features extracted form a dataset of images of defected and healthy slabs are used to train a computer vision based system while another dataset is used to evaluate the proposed algorithm. Initial results show that the proposed algorithm is able to detect the existence of defects with about 77% success rate.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Khaled Assaleh, Tamer Shanableh, and Sherif Yehia "Artificial intelligence and signal processing for infrastructure assessment", Proc. SPIE 9437, Structural Health Monitoring and Inspection of Advanced Materials, Aerospace, and Civil Infrastructure 2015, 94372O (1 April 2015); https://doi.org/10.1117/12.2179920
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
General packet radio service

Inspection

Image processing

Feature extraction

Detection and tracking algorithms

Bridges

Defect detection

Back to Top