Automated Data Collection System of Pavement Distresses: Development, Evaluation & Validation of Distress Types and Severities

Abstract

This study presented an affordable and simpler technique that does not require complex technology and is suitable for middle size road networks. This technique involves taking pictures of various sections of the road network using cameras that can be mounted on public vehicles and transmitting taken images to a processing center. Each image is processed using image filtering techniques to produce an initial estimate of the PI. A total of 5,070 images and 507 sections (4 x 10 m per section) were taken and tested on a part of the Sheikh Maktoum Bin Rashid Highway E11 in Abu-Dhabi city (UAE) based on the quantity and clarity of the distresses. Six types of pavement distresses were tested; (1) longitudinal cracking, (2) alligator cracking, (3) block cracking, (4) pothole distress, (5) transverse cracking and (6) edge cracking. Three severity levels were considered: (1) low, (2) medium and (3) high. There were two distress measurement methods used to identify pavement distresses; semi-automated measurement (SAM) method and automated measurement (AM) method. In order to evaluate the accuracy of the AM method, two expert observers were used individually to extract the pavement distress by using the SAM method. The Cohen’s weighted Kappa used to determine the agreement between the two observers. The overall agreement result of the pavement distresses between the two observers was 98%, which is almost a perfect agreement. The overall agreement result of the pavement distresses between the two measurement methods was 89%, which is again an almost perfect agreement. In addition, the AM method validated by using R2 method and was found to be 0.93. The weighted mean speed of all distresses and standard deviation were found to be 58.56 km/h and 28.24 km/h respectively.