Assessment of cracks on concrete bridges using image processing supported by laser scanning survey

Abstract The accurate assessment of the state of conservation of concrete bridges is extremely important to define maintenance strategies and to optimize interventions. In this regard, crack detection and characterization plays a particularly important role. However, several limitations are found in current evaluation techniques. In fact, these are work-intensive, prone to human error, and they often require the use of expensive inspection means, such as under-bridge trucks. In this scope, the development of automatic methods based on image processing and laser scanning to assess cracks in bridges has significant advantages. In this paper a novel method, MCrack-TLS, is proposed to automatically assess cracks in concrete bridges, based on the combination of image processing and terrestrial laser scanning (TLS) technology. The images captured are orthorectified by geometric information surveyed by TLS, solving one of the major drawbacks of applying image processing for cracks characterization on large structures. After an experimental characterization, the method was tested on a concrete viaduct at IC2 road, in Rio Maior, Portugal, herein adopted as case study for onsite validation. It should be noted that capturing images with the required characteristics involves the use of different equipment, depending on both location and type of structural members. The results show the high potential of MCrack-TLS, namely its increased productivity and the possibility of record all data processed, and add it to 3D point clouds, creating 3D models of the state of conservation of bridges. In addition, it avoids the exposure of bridge inspectors to dangerous situations.