Abstract

The Utilization of Unmanned Aerial Vehicle (UAV) as a vehicle for comprehensive and fast road condition data acquisition is expected to minimize or even replace conventional road condition surveys in the field. In addition, the final UAV product in the form of a 2D/3D model of road conditions has been proven to be used as a medium for interpreting road damage and measuring the dimensions of road damage without having to do it in the field. The significant difference between this study and other studies is found in the use of the Surface Distress Index and Pavement Condition Index methods for assessing road conditions on the 2D/3D model of the UAV results. No research compares the use of the two methods in 2D/3D models. This research took photos of pavement conditions using drones to produce 2D and 3D models as visual media for assessing pavement conditions using the Pavement Condition Index and Surface Distress Index methods. The results of the assessment on the model compared with the assessment in the field. In comparison, the dimension level of accuracy of pavement distress in the model against the results of manual measurements in the field, edge cracking has the lowest accuracy value of 75.72%, and joint reflective crack has the highest accuracy value of 97.86%. The linear regression equation for the Pavement Condition Index method in the model against manual in the field is y = 0.931x + 3.6003 with a coefficient of determination r2 = 0.86 and an MSE of 121.333, while the linear regression equation for the Surface Distress Index method in the model against manual in the field is y = 0.5831x + 28.867 with a coefficient of determination that is r2 = 0.653 and MSE = 2115. Based on the comparison above, in this study, the application of UAV for pavement condition assessment is more precise using the Pavement Condition Index method.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call