Artificial intelligence system for detection and classification of flexible pavement crack’s severity / Anas Ibrahim ... [et al.]

Effective road maintenance system is vital to safeguard traffic safety, serviceability, and prolong the life span of the road. Traditional practices based on manual visual observation in the inspection of distressed pavements is no longer effective in vast networking of our existing road infrastructures. Manual method of inspection is laborious, time consuming and poses safety hazard to the maintenance workers. This project focuses in utilizing an Artificial Intelligence (AI) method to automatically classify pavement crack severity. Field data verification was performed to validate accuracy and reliability of the crack’s severity prediction based on AI. Several important phases are required in research methodology processes including data collection, image labelling, image resizing, image enhancement, deep convolution neural network (DCNN) training and performance evaluation. Throughout the analysis of image processing results, the image output was successfully classified and the good agreement between field measurement data and DCNN prediction of crack’s severity validated the reliability of the system up to 93.30%. In conclusion, the automation system is capable to classify the crack’s severity based on the JKR guideline of visual assessment.