Automated Bridge Deck Evaluation through UAV Derived Point Cloud

Imagery-based, three-dimensional (3D) reconstructions from Unmanned Aerial Vehicles (UAVs) hold the potential to provide a safer, more economical, and less disruptive approach for bridge inspection. This paper describes a methodology using a low-cost UAV to generate an imagery-based, dense point cloud for bridge deck inspection. Structure from motion (SfM) is employed to create a three-dimensional (3D) point cloud. Outlier data are removed through a density-based filtering method. Next, the unsupervised learning algorithm k-means and an object-based region growing algorithm are compared for accuracy with respect to bridge deck extraction. Last, an automatic pavement evaluation method is proposed to estimate the deck’s pavement condition. The procedure is demonstrated through an actual case study, in which a 3D point cloud of 16 million valid points was generated from 212 images. With that data set, the region growing method successfully extracted the deck area with an F-score close to 95%, while the unsupervised learning approach only achieved 76%. In the last, to evaluate the surface condition of the extracted pavement, a polynomial surface fitting method was designed to evaluate and visualise the damages.