Deep learning for masonry lined tunnel condition assessment

The condition assessment of masonry lined railway tunnels typically involves manually identifying lining defects from photographic and lidar surveys taken of the tunnel intrados. This process is time-consuming and subjective to the assessor's judgement. However, recent developments in machine l...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Expanding Underground - Knowledge and Passion to Make a Positive Impact on the World S. 2910 - 2917
Hauptverfasser: Smith, J., Paraskevopoulou, C., Bedi, A., Invernici, M.
Format: Buchkapitel
Sprache:Englisch
Veröffentlicht: United Kingdom CRC Press 2023
Taylor & Francis Group
Ausgabe:1
Schlagworte:
RGB Image
Depth Map
Masonry Joints
Geological Strength Index
Significant Efflorescence
Overburden
Point Cloud
Tunnel Lining
Watershed Algorithm
Proposed Change Detection Methods
Tunnel Inspection
RGB Data
Above Ground
Digital Image Correlation
TLS Survey
Point Cloud Data
Masonry Tunnel
BIM Model
Block Segmentation
RGB
Lidar Data
Multiview Approach
SEM
SCL
Concrete Tunnel Lining
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The condition assessment of masonry lined railway tunnels typically involves manually identifying lining defects from photographic and lidar surveys taken of the tunnel intrados. This process is time-consuming and subjective to the assessor's judgement. However, recent developments in machine learning achieve the quality metrics required to automate the detection of defects from noisy and irregular tunnel data, offering the potential to reduce tunnel assessment and maintenance costs. This paper proposes a deep learning workflow for defect segmentation. The method is evaluated on the task of masonry block segmentation from lidar data. Acceptable performance is achieved on a sample tunnel section, suggesting that similar methods are applicable to other masonry lined tunnel defect segmentation tasks.
DOI:10.1201/9781003348030-351