1 AIT Asian Institute of Technology

Development of heuristic tools for image based crack inspection and monitoring of concrete building components

AuthorMishra, Eshanta
Call NumberAIT Thesis no.ST-19-12
NoteA thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Structural Engineering, School of Engineering and Technology
PublisherAsian Institute of Technology
Series StatementThesis ; no. ST-19-12
AbstractThe rapid evolution of cameras and drones in the past few years have paved a way for imagebased inspection and monitoring of buildings and tall structures. Infrastructures need periodic inspection to ensure that they are performing as intended and do not pose risks to public health and safety. This study presents a framework for the development of a fully automated imagebased structural inspection and monitoring system. Element level images of the structural components are acquired, and its properties are obtained from the corresponding BIM (Building Information Modeling) model. The image of the structural member along with its dimensions is then fed to an image processing algorithm which automatically detects cracks in concrete surfaces and measures the crack parameters. A machine learning algorithm trained on several synthetic crack scenarios automatically predicts the severity of each cracks based on these parameters. The detected cracks are then color coded and are mapped back to the BIM model so that the current structural state can be effectively visualized. The system also helps predict the corrective action to be taken for the maintenance of the structural element based on its severity level. Using several examples of images of real structural members, it is demonstrated that the system for the detection of cracks, measurement of the crack parameters and prediction of severity shows fairly accurate results. Apart from being a smart and convenient tool for structural inspection, the developed framework also results in better operations, planning and facility management.
Year2019
Corresponding Series Added EntryAsian Institute of Technology. Thesis ; no. ST-19-12
TypeThesis
SchoolSchool of Engineering and Technology
DepartmentDepartment of Civil and Infrastucture Engineering (DCIE)
Academic Program/FoSStructural Engineering (STE) /Former Name = Structural Engineering and Construction (ST)
Chairperson(s)Pennung Warnitchai;Anwar, Naveed;
Examination Committee(s)Punchet Thammarak;Raktipong Sahamitmongkol;
Scholarship Donor(s)His Majesty the King’s Scholarship (Thailand);
DegreeThesis (M.Eng.) - Asian Institute of Technology, 2019


Usage Metrics
View Detail0
Read PDF0
Download PDF0