Pavement health 4.0: a novel AI-enabled PavementVision approach for pavement health monitoring and classification

Abstract

To determine the extent of pavement damage and forms of pavement distress, road pavement conditions must be precisely assessed. As a result, monitoring systems are regarded as an important stage in the maintenance procedure. In recent times, numerous investigations have been carried out to track the condition of pavement and monitor road surfaces. In the undertaken study, we have proposed a novel artificial intelligent (AI) and computer vision-enabled PavementCarevision 4.0 approach to detect and classify pavement health conditions i.e., defects. In this study, a customized pavement-2000 dataset has been designed which contains more than 2,000 images of a variety of pavement defects. In the initial phase, we preprocessed and enhanced pavement images using the customized adjustable linear contrast enhancement methodology. The enhanced pavement image samples were fed to the proposed customized YOLOV8 enabled PavementHealth 4.0 framework for pavement condition detection of a variety of pavement defects such as longitudinal cracks, alligator cracks, transverse cracks, and potholes. The proposed customized YOLOV8 enabled PavementHealth 4.0 framework has achieved an accuracy of 99.20 percent; an receiver operating characteristic (ROC) value of 0.98 and outperformed existing AI-based state-of-the-art methodologies such as pose NET, YOLOv7, YOLOv5, long short-term memory network (LSTM), Mask region-based convolutional neural network (R-CNN), and decision tree.