A Survey on Surface Crack Detection in Concretes using Traditional, Image Processing, Machine Learning, and Deep Learning Techniques

Abstract

Concrete surface cracks are the first signs of structural deterioration that is crucial for repair, as well as constant exposure that can result in structural health and durability, so it should be addressed as early as possible to prevent additional damage. Usually, cracks are visually monitored by inspectors who record data regarding presence, location, and width. Manual visual inspection is often deemed ineffective in terms of cost, protection, accuracy of assessment and reliability. As moving with the fast face of technology advancements, the possibility of the information technology driven methodologies in constructions field are also getting wide visibility. The automated surveillance and monitoring system are very common in every phases of the construction and maintenance of structures. In Surface Crack detection different technology backed automated systems outperforms the traditional manual inspection and crack detection. With the help different computational aids like Image Processing, Machine Learning and Deep Learning techniques, the images and videos captured from surveillance site are analyzing for automated crack detection. In this work a detailed study of such different automated methods and techniques which are efficient in terms of accuracy, time, cost effectiveness, feasibility are going to be projected. This work also focus on finding the research gap in this field with rigorous and evaluation to open up the new possibilities.