Automated Robotic Monitoring and Inspection of Steel Structures and\n Bridges

Abstract

This paper presents visual and 3D structure inspection for steel structures\nand bridges using a developed climbing robot. The robot can move freely on a\nsteel surface, carry sensors, collect data and then send to the ground station\nin real time for monitoring as well as further processing. Steel surface image\nstitching and 3D map building are conducted to provide a current condition of\nthe structure. Also, a computer vision-based method is implemented to detect\nsurface defects on stitched images. The effectiveness of the climbing robot's\ninspection is tested in multiple circumstances to ensure strong steel adhesion\nand successful data collection. The detection method was also successfully\nevaluated on various test images, where steel cracks could be automatically\nidentified, without the requirement of some heuristic reasoning.\n