Image-based Detection of Surface Defects in Concrete during Construction

Construction defects are costly for the economy. The cost of defect elimination is between 2% and 12.4% of the total cost of construction [1] and much time and effort is required to inspect construction sites and document defects [2]. Automating the inspection of construction projects would free up resources and may even enable more frequent inspections, leading to more efficient construction projects. The progress in CV and ML may enable the complete automation of this process in the future. Although deep learning is applied to many different fields, research into image-based defect detection using deep learning is still limited in the construction industry, despite its large size, and focuses on security, progress, and productivity. In contrast, there appear to be relatively few publications on methods utilized for object detection in quality assurance in construction. So far, the research into detecting defects has been mainly limited to defects occurring in the maintenance phase of infrastructure facilities such as roads, bridges, and sewer systems.