YOLOv8-Based Road Sign Detection Algorithm Incorporating CBAM and DWConv

Detecting road signs is essential for autonomous driving technology, especially in the identification of small objects.To overcome the difficulties of identifying tiny road signs, In order to increase detection performance, this work proposes an enhanced YOLOv8 method that combines Depthwise Separable Convolution (DWConv) with the Convolutional Block Attention Module (CBAM). Specifically, YOLOv8 serves as the baseline model, which is optimized in the feature extraction, fusion, and detection stages. The CBAM attention mechanism is incorporated into the Neck section, while traditional convolutions are replaced with DWConv, improving the model's focus on tiny information while reducing computational complexity. To improve the model's generalization ability, data augmentation methods like Mosaic and Mixup are incorporated. Mosaic augmentation increases the diversity of training data by stitching different images together, whereas Mixup improves the models adaptability to various scenes by blending images. Additionally, common augmentation techniques, including cropping, color adjustment, and flipping, are effectively applied to optimize model performance. Experimental results indicate that, compared with YOLOv8n, the improved YOLOv8 algorithm achieves a 2.1 percentage point increase in mean Average Precision (mAP0.5), a 4.9% improvement in mAP50-95, and a 7.2% increase in recall rate. Furthermore, the algorithm significantly reduces the missed detection rate and improves small-object detection performance while lowering runtime by 4.1%. These results demonstrate the practical applicability of the proposed method.