Crack detection, identification and classification are essential steps in pavement management system. It helps the agency in determining the appropriate rehabilitation technique to be done on the pavement. Typically, crack detection is done by manually checking images captured from road survey however it is uneconomical and time-consuming. In this study, a two-step sequential automated process detecting cracks and classifying severity of asphalt pavements is proposed. Mask RCNN was used in detecting and identifying linear and fatigue cracks (with severity) while image processing was used in determining the severity of linear crack. The Mask RCNN model used 21,150 images for training, composed of longitudinal, transverse and fatigue cracks of different severity levels. In addition, 5,657 and 5,756 images were utilised for validation and testing, respectively. The results showed that the Mask RCNN model can be used in detecting and identifying pavement cracks with an average accuracy of 92.10% while image processing was found to have a correlation coefficient of 0.85 when compared with field measured crack width and an accuracy of 87.5% in classifying linear cracks severity. The proposed method was found to be a promising approach in detecting cracks and classifying the corresponding severity of asphalt pavements.

Pavement management systems include road surveying, data analysis, identification of rehabilitated sections, determination of treatment methods, and budget optimization for maintenance and rehabilitation (M&R). These complex processes challenge many agencies in determining the most appropriate M&R strategies for the current year and choosing rehabilitation alternatives using life cycle cost analysis. In addition, these are time-consuming processes since the analysis and interpretation are done separately. In this study, an automated integrated algorithm is developed to help agencies determine the appropriate rehabilitated homogeneous section and optimize the budget at the network level for single and multilane roads. The algorithm was developed based on the pruned exact linear time and changepoints for a range of penalties methods in determining homogeneous sections from distresses on the surfaces being surveyed on single lanes. An additional algorithm is then proposed to identify homogeneous sections by considering adjacent multilane sections. Finally, the prioritized homogeneous sections for rehabilitation are determined by optimizing the available budget at the network level, considering the distress index and recommended rehabilitation type. During optimization, different budget constraint scenarios were considered to satisfy several requirements from agencies considering a random search approach. The proposed algorithm was applied to real field data where it was found that the recommended M&R strategies for the homogenized sections using the proposed approach are feasible, practical, and reasonable. It is recommended that the performance model used in this study be developed further to improve the proposed integrated algorithm.