Automated Defect Detection and Visualization for the Robotic Airport Runway Inspection
Zhongcheng Gui, Haifeng Li
Abstract
Detection of both surface and subsurface defects is a vital task for maintaining the structural health and reliability of airport runways. We report the automated data collection and analysis for airport runways based on our novel robotic system, which employs a camera and a GPR (Ground Penetrating Radar) to inspect the surface and subsurface conditions, respectively. To perform the automated data analysis, we propose a novel crack detection algorithm based on the images, and a subsurface defect detection method with GPR data. Additionally, to create a composite global view of a large airport runway span, a camera/GPR data sequence from the robot is aligned accurately to create a continuous mosaic for visualization. We combine these algorithms into a software to perform automated on-site analysis. We have put our robot and software into engineering practice over 20 airports in China, achieving the performance of 70% and 67% F1-measure for crack detection and subsurface defect detection, respectively. More importantly, the results of our algorithms can satisfy the requirement of applications.