Addressing challenges such as large memory footprint, high computational complexity, and insufficient real-time detection speed in road crack detection models for complex scenarios, a highly efficient and precise algorithm named FCG-YOLO is proposed in this study. Lightweight modules and attention mechanisms are integrated, and traditional feature fusion pyramids are enhanced.The algorithm incorporates PConv into the residual calculation module of YOLOv8n to introduce the improved C2f_Faster structure, thereby reducing model parameters and computational complexity. To enhance detection accuracy, a global attention mechanism (GAM) is introduced into the backbone, and the Feature Fusion Pyramid SPPF is improved to SPPFCSPC module, enhancing the model"s ability to represent and fuse features of road cracks.The impact of each module on algorithm performance is verified through ablation experiments, identifying a lightweight and accurate model configuration. Furthermore, the robustness and generalization of the algorithm are explored in practical application scenarios.FCG-YOLO demonstrates outstanding detection efficiency, achieving a detection accuracy of 90.3% mAP50 and 74.4% mAP50-95 on the validation set, with a detection speed of 345 frames per second. These results highlight its high detection efficiency and significant practical value.