Application of Combining YOLO Models and 3D GPR Images in Road Detection and Maintenance

Abstract

Improving the detection efficiency and maintenance benefits is one of the greatest challenges in road testing and maintenance. To address this problem, this paper presents a method for combining the you only look once (YOLO) series with 3D ground-penetrating radar (GPR) images to recognize the internal defects in asphalt pavement and compares the effectiveness of traditional detection and GPR detection by evaluating the maintenance benefits. First, traditional detection is conducted to survey and summarize the surface conditions of tested roads, which are missing the internal information. Therefore, GPR detection is implemented to acquire the images of concealed defects. Then, the YOLOv5 model with the most even performance of the six selected models is applied to achieve the rapid identification of road defects. Finally, the benefits evaluation of maintenance programs based on these two detection methods is conducted from economic and environmental perspectives. The results demonstrate that the economic scores are improved and the maintenance cost is reduced by $49,398/km based on GPR detection; the energy consumption and carbon emissions are reduced by 792,106 MJ/km (16.94%) and 56,289 kg/km (16.91%), respectively, all of which indicates the effectiveness of 3D GPR in pavement detection and maintenance.

Two-stage method based on the you only look once framework and image segmentation for crack detection in concrete structures

“…The YOLO framework has been successfully used in several diverse applications of civil engineering, such as pedestrian detection [46], real-time face detection [47], license plate detection [48], spilled load detection on freeways [49], pothole detection [50], traffic load distribution detection [51], worker and heavy construction equipment identification on site [52], building component identification [53], rebar diameter estimation [54], building footprint estimation [55], traffic management [56], pavement distress detection [57], crack detection [58][59][60][61], and maintenance [62][63][64]. The following sections describe the details of the structure of YOLOv5.…”

Automatic Detection and Assessment of Pavement Marking Defects with Street View Imagery at the City Scale

“…In the entire process of urban roadway maintenance, street-view imageries are the results of the first step of daily monitoring. They can be effectively used to achieve quantitative assessment as the second step, and the assessment results can help in the third step of the decision-making and the fourth step of execution [5].…”

“…In smart cities, urban management should be intelligent, efficient, and sustainable, which requires the capability of systematic processes [4]. The entire process of maintaining urban roadways can be divided into four steps: daily monitoring, quality assessment, decisionmaking, and execution [5]. There is a need for cooperation between data providers who supply daily monitoring, technology providers who can offer quality assessment and decision-making, and local authorities who are responsible for the execution; thus, a systematic process can be achieved [3].…”

Hyperbola detection with Retinanet: application to new sites and scalability

“…Machine learning methods became widely used in the last decades in geophysical applications and also in the context of ground penetrating radar (GPR) to automatically detect pipes and rebar or tree roots based on automatic hyperbola picking (e.g. Gamba & Lossani 2000;Shaw et al 2005;Lei et al 2019;Liu et al 2021). From the hyperbolas' shape one can derive the velocity of the electromagnetic waves in the overlying material, which is needed for exact depth determination.…”