RBL-YOLOv8: A Lightweight Multi-Scale Detection and Recognition Method for Traffic Signs

To address the problems of misdetection, omission, and low accuracy in traffic sign detection and recognition, a novel method called RBL-YOLOv8 is presented by improving YOLOv8. In the feature extraction network, the RepNC-SPELAN module is used to replace the C2f module to improve the feature extraction capability and reduce the number of parameters. In the feature fusion network, fusion of largescale feature layers is added, while weighted feature fusion is used to create cross-layer connections between shallow and deep features to improve the utilisation of shallow features for better detection of small targets. A lightweight detection head is proposed to reduce the number of parameters and computational complexity of the model, while improving the localization and classification ability of the detection head. The MPDIoU loss function is used to replace CIOU, which can better accelerate the bounding box regression. The improved model is conducted experiments on the CCTSDB and TT100K datasets and compared with other algorithms, the results validate its effectiveness and superiority.