Enhanced Crack Segmentation Algorithm Using 3D Pavement Data

Abstract

Automatic pavement crack segmentation has gained attention among researchers and transportation agencies over the past two decades. However, most existing algorithms using two-dimensional (2D) pavement intensity images cannot provide a satisfactory performance. With the advent of sensing technology, three-dimensional (3D) line laser pavement imaging systems have become available. The objective of this paper is to propose an enhanced dynamic optimization algorithm employing the advantages of 3D pavement data to improve crack segmentation. The proposed algorithm consists of three major stages. First, a two-step Gaussian filter is applied to remove outliers from the collected laser data and rectify the profile in order to reduce the influence of cross-slope and ruts on crack segmentation. Then, a rough crack segmentation stage is conducted to adaptively identify the crack regions of interest. Finally, a bounding box and major orientation for each valid crack region of interest will provide searching space and direction for the precise crack segmentation using the dynamic optimization algorithm. Experimental tests were conducted using actual pavement data collected near Savannah, Georgia. The four most common types of pavement cracking (longitudinal, transverse, block, and alligator cracking), as well as distress-free pavements, are tested, and the performance between original dynamic optimization algorithm and the proposed algorithm is compared. Experimental results show that the proposed algorithm take only about 1/4 of the average computation time of the original algorithm. Also, the accuracy of crack segmentation has been improved since the proposed algorithm removes the unnecessary false positives and handles cracks in multiple directions better. Finally, conclusions are drawn, and recommendations for future research are discussed.