Machine vision techniques for condition assessment of civil infrastructure
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Abstract
Manual visual inspection is the main form of assessing the physical and functional conditions of civil infrastructure at regular intervals to ensure the infrastructure still meets its present service requirements. In addition to this form of inspection, several novel machine vision techniques are gradually becoming available. They promise to reduce the time needed to inspect facilities and standardize the quality of the results by removing human judgment as a factor of variability. This chapter explains the origins and a representative selection of these methods and gives a sneak peak of future trends in machine vision techniques in assessing civil infrastructure conditions. This chapter starts with the introduction of the current practices of civil infrastructure condition assessments. Then, the state-of-the-art machine vision techniques available for the condition assessment of civil infrastructure are described. The benefits and limitations of each technique are discussed, and the challenges of using the techniques are highlighted. Several case studies are presented to show the effectiveness of these techniques in assessing the conditions of civil infrastructure, such as bridges, buildings, and roads.