A well-functioning road network is essential to an efficient transportation system. Both the United States and Europe have road monitoring and safety inspection organizations to ensure roads and bridges are maintained to a safe standard. Today, the current maintenance practice is via manual detection, which has a variety of limitations (e.g., labor and cost intensive, requires road closures, and places inspectors in harm’s way). Is there a more automated and efficient means of monitoring our road networks? Researchers looked to unmanned aerial vehicle imaging and 3D reconstruction models in a recent study in the Journal of Surveying Engineering.
In their article, “Volumetric Pothole Detection from UAV-Based Imagery,” authors Siyuan Chen, Debra F. Laefer, Xiangding Zeng, Linh Truong-Hong, and Eleni Mangina propose an automated pothole detection and evaluation algorithm by focusing on damage extraction. Their research methodology encompasses the following steps: 1) data acquisition using UAV imaging; 2) 3D reconstruction of 2D images; 3) data filtering based on a structure-from-motion (SfM) algorithm to generate a point cloud; and 4) pothole extraction. Once they finalized the workflow, the authors conducted field trials to benchmark their proposed algorithm. Learn more about their new application for UAVs to evaluate roadways at https://doi.org/10.1061/JSUED2.SUENG-1458. The abstract is below.
Abstract
Road networks are essential elements of a community’s infrastructure and need regular inspection. Present practice requires traffic interruptions and safety risks for inspectors. The road detection system based on vehicle-mounted lasers is also quite mature, offering advantages such as high-precision defect detection, high automation, and fast detection speed. However, it does have drawbacks such as high equipment procurement and maintenance costs, limited flexibility, and insufficient coverage range. Therefore, this paper proposes a low-cost unmanned aerial vehicle (UAV)-based alternative using imagery for automatic road pavement inspection focusing on pothole detection and classification. A slicing-based method, entitled the Pavement Pothole Detection Algorithm, is applied to the imagery after it is converted into a three-dimensional point cloud. When compared with manually extracted results, the proposed UAV-structure-from-motion (SfM) method and the associated algorithm achieved 0.01 m-level accuracy for pothole depth detection and maximum errors of 0.0053 m3 in volume evaluation for cases studies of both a road and a bridge deck.
Find out how to combine UAV observations with an algorithm to better detect and improve maintenance of potholes in the ASCE Library: https://doi.org/10.1061/JSUED2.SUENG-1458.
