3D reconstruction and measurement of concrete spalling using near-field photometric stereo and YOLOv8

Dow, Hamish and Perry, Marcus and Pennada, Sanjeetha and Lunn, Rebecca and Pytharouli, Stella (2024) 3D reconstruction and measurement of concrete spalling using near-field photometric stereo and YOLOv8. Automation in Construction, 166. 105633. ISSN 0926-5805 (https://doi.org/10.1016/j.autcon.2024.105633)

[thumbnail of Dow-etal-AC-2024-3D-reconstruction-and-measurement-of-concrete-spalling]
Preview
 Text. Filename: Dow-etal-AC-2024-3D-reconstruction-and-measurement-of-concrete-spalling.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (6MB)| Preview

Abstract

Current concrete spalling detection and measurement methods are sparse; despite recent research and commercial offerings using laser scanners, manual measurement is still the industry standard. This paper presents a spalling 3D reconstruction and measurement method. The method uses images illuminated with angled and directional lighting and three neural networks for Photometric stereo 3D mesh generation and spalling volume measurement. The proposed method was benchmarked on a laboratory dataset of spalled concrete slabs against a high-resolution laser scanner, yielding an average height error of 0.0 mm and a standard deviation of 1.3 mm. Volume comparisons showed that with manual input, the method achieved a mean absolute percentage error of 22%. Finally, the proposed technique was compared to manual measurements and benchmarked on a spalled concrete structure against a Trimble X12 laser scanner. This research can provide inspectors with increased data interpretability and reduced imaging time for concrete defect mapping.

ORCID iDs

Dow, Hamish ORCID logoORCID: https://orcid.org/0000-0002-1431-7063, Perry, Marcus ORCID logoORCID: https://orcid.org/0000-0001-9173-8198, Pennada, Sanjeetha, Lunn, Rebecca ORCID logoORCID: https://orcid.org/0000-0002-4258-9349 and Pytharouli, Stella ORCID logoORCID: https://orcid.org/0000-0002-2899-1518;
CORE (COnnecting REpositories)