Analysis of tunnel GPR image based on Convolutional Neural Networks with single-stage and two-stage detections
- Document Type
- Publications · Book
- Registered DB
- Scopus
- Journal
- Smart Geotechnics for Smart Societiespp.972 · 2023
- Citation
- Scopus 1
- FWCI (Scopus)
- 0.49
Authors
- Bae, ByongkyuFirst authorDepartment of Civil and Environmental Engineering, Pusan National University, Busan, Republic of South Korea
- Ahn, JaehunDepartment of Civil and Environmental Engineering, Pusan National University, Busan, Republic of South Korea
- Jung, DuHwoeDepartment of Civil Engineering, Pukyong National University, Busan, Republic of South Korea
- Jung, HyunjunDepartment of DX, Korea Authority of Land & Infrastructure Safety (KALIS), Jinju, Republic of South Korea
- Yoo, ChangkyoonDepartment of Tunnel, Korea Authority of Land & Infrastructure Safety (KALIS), Jinju, Republic of South Korea
Abstract
Maintenance of tunnel structure involves investigation of tunnel wall with Ground Penetration Radar (GPR). By analyzing GPR investigation images, engineers determine the locations of steel ribs, thickness of concrete lining and the location and size of void if any. The identification of defects, however, requires experience and also is a time-consuming work. YOLO (You Only Look Once) and Mask R-CNN are CNN (Convolutional Neural Network) algorithms with single-stage detection and two stage detection, respectively. In this study, a model based on YOLO was trained to detect the steel ribs in GPR images and Mask R-CNN was trained to detect the concrete lining, and tested. Overall, both of the CNN algorithms provided satisfactory results; however, the images with severe scattering resulted in lower accuracy.
Keywords
Convolutional Neural NetworkGPRImage DetectionMask R-CNNYOLOv5
Identifiers
- Scopus EID
- 2-s2.0-85171003243



Login
Back to Publication list