The research focuses on the development of intelligent grid-based crack detection algorithms and antiroad shadow algorithms, with the following significance. Value of developing end-to-end grid-based detection algorithms: Theoretical significance: Grid-based detection simultaneously captures the morphology and affected area of cracks, providing a more accurate reflection of road surface damage, which is beyond the capabilities of target detection and pixel-level segmentation; Policy relevance: Grid-based detection corresponds to the national standards for automated detection, serving as a necessary condition for intelligent detection on a nationwide scale; Practical applications: Grid-based detection is simpler compared to pixel-level detection tasks, enabling easier and more efficient deployment and application. Value of developing algorithms for shadow suppression: Economic benefits: Implementing shadow suppression minimizes the need for additional lighting, resulting in energy savin...

To address two key challenges—limited grid-level detection capability and difficulty in detecting pavement cracks in complex environments, this study proposes a novel neural network model called CrackcellNet. This innovative model incorporates an output structure that enables end-to-end grid recognition and a module that enhances shadow image data to enhance crack detection. The model relies on the design of consecutive pooling layers to achieve adaptive target size grid output. By utilizing image fusion techniques, it enhances the quantity of shadow data in road surface detection. The results of ablation experiments indicate that the optimal configuration for CrackcellNet includes V-block and shadow augmentation operations, dilation rates of 1 or 2, and a convolutional layer in the CBA module. Through extensive experimentation, we have demonstrated that our model achieved an accuracy rate of 94.5% for grid-level crack detection and a F1 value of 0.839. Furthermore, practical engineeri...