Premium
Machine learning and image processing approaches for estimating concrete surface roughness using basic cameras
Author(s) -
Valikhani Alireza,
Jaberi Jahromi Azadeh,
Pouyanfar Samira,
Mantawy Islam M.,
Azizinamini Atorod
Publication year - 2021
Publication title -
computer‐aided civil and infrastructure engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.773
H-Index - 82
eISSN - 1467-8667
pISSN - 1093-9687
DOI - 10.1111/mice.12605
Subject(s) - aggregate (composite) , computer science , surface roughness , surface finish , process (computing) , retrofitting , surface (topology) , image processing , artificial intelligence , computer vision , engineering drawing , machine learning , image (mathematics) , materials science , structural engineering , mathematics , engineering , composite material , geometry , operating system
Casting concrete at different ages for new construction and repairing or retrofitting concrete structures requires a sufficient bond between concrete casts. The bond strength between different casts is attributed to surface roughness. Surface roughness can be achieved in many ways, such as water‐jetting or sandblasting. To evaluate the degree of surface roughness, qualitative and quantitative methods are introduced by many researchers; however, several drawbacks are associated with most of these methods, including cost, availability, human errors, and inability to assess old structures from prior inspection records. Two novel industrial implementation methods are introduced in this paper to estimate, quantitatively, the concrete surface roughness from images with sufficient resolution. In the first application method, a digital image processing method is proposed to distinguish the coarse aggregate from cement paste, and a new index is presented as a function of aggregate proportional area to the surface area. In the second application method, data augmentation and transfer learning techniques in computer vision and machine learning are utilized to classify new images based on predefined images during the learning process. Both application methods were related to a well‐established method of 3D laser scanning from sandblasted concrete surfaces. Finally, a brand new set of images of sandblasted surfaces was used to test and validate both methods. The results show that both methods successfully estimate the concrete surface roughness with an accuracy of more than 93%.