Automatic Detection and Evaluation of 3D Pavement Defects Using 2D and 3D Information at the High Speed

Abstract

This paper presents a technique of automatic 3D pavement defects detection using both the two-dimensional (2D) and three-dimensional (3D) information from the images captured at high speed. Scaled 3D points reconstructed from Structure from Motion algorithm are first used to detect the defect regions based on the 3D information. A mismatched points rejection method then eliminates incorrectly matched points and reconstructs a final 3D road surface. The proposed technique uses both 3D and 2D information for the defects detection where the characteristics of defect regions in 2D images together with the 3D information from the 3D reconstruction detect the defect region. The capability of the proposed technique was first investigated through parameters studies. Quantitative analyses have shown the accuracy, precision, and recall rate of the proposed technique are all above 90%. The result demonstrates the potential of the proposed technique for the automatic detection of 3D pavement defects.