CNN-based pavement defects detection using grey and depth images

This paper introduces a method for detecting pavement defects based on convolutional neural networks. First, grey and depth image data were acquired using a 3D pavement information collection system, followed by preprocessing and labelling of the data. Subsequently, two network structures were developed to accommodate the image data characteristics: classic U-shaped and double-headed structures. Attention modules were integrated into the models to enhance the accuracy of defect detection. Finally, a quantitative analysis of four types of pavement defects was conducted. The numerical evaluation results demonstrated that training the network with a combination of grey and depth images significantly improves the detection accuracy, resulting in a 10% enhancement in mean intersection over union (MIoU). The proposed model attained a global pixel accuracy (GPA) of 97.36% and an MIoU of 80.28%. The proposed network model was found to have an increased focus on the pavement defect areas, making it highly effective.