Bill Spencer, Nathan M. & Anne M. Newmark Endowed Chair in Civil Engineering, University of Illinois Urbana Champaign

Abstract: Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This presentation provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure inspection and monitoring. In particular, relevant work in the fields of computer vision, machine learning, and structural engineering are presented. The applications reviewed are classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image, with focus on rapid structural condition assessment of bridges and buildings after disasters. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurements of displacement and modal analysis, with application to inland waterway networks. The paper concludes with a discussion of promising areas of growth for research in the field of computer vision-based civil infrastructure inspection and monitoring, which will ultimately lead to smarter civil infrastructure.