Deep Learning-Based Detection, Segmentation, and Quantification of Asphalt Pavement Cracks

The primary factor influencing road performance is pavement deterioration. Pavement cracking, a prevalent form of road deterioration, is a significant challenge in road maintenance. This paper proposes a method utilizing deep convolutional neural network models for precise crack detection, segmentation, and geometric parameter calculation in pavement crack identification. The system operates through three primary stages: Commencement, crack identification employs YOLOv10, a rapid and efficient object detection model. Secondly, crack segmentation employs a modified Unet 3+ variant known as Residual-Attention UNet 3+, which effectively distinguishes crack pixels from the background by utilizing attention mechanisms and residual connections to enhance accuracy. Finally, crack quantification, wherein the system computes the crack's geometric parameters, including width, length, angle, and orientation. We assessed performance using two datasets: SUT-Crack, a publicly accessible dataset, and IRD-Crack, a new real-world dataset compiled by the authors from roads in Diyala, Iraq, with diverse lighting conditions and surface complexities. The suggested technique attained an accuracy of 98.96% on the SUT-Crack dataset. It showed superior performance on the IRD-Crack dataset under actual situations, therefore validating its efficacy and generalization capability. This method offers a pragmatic and computationally efficient instrument for monitoring pavement cracks and can facilitate road repair choices.