Traffic sign detection algorithm with occlusion awareness and edge enhancement

To address the challenges of detecting long-distance small-size traffic signs and the low recognitionaccuracy in scenarios with background interference and occlusion, we propose the MSED-YOLOv8detection framework. The MFE (Multi-scale Feature Enhancement) module employs dynamic upsamplingand hybrid pooling to align multi-scale features and mitigate feature information loss. TheSMSA (Shielding-aware Multi-Scale Attention) mechanism filters important features through twodimensionalspatial-channel screening and integrates them into the network head to enhance featureinformation and improve robustness in occlusion scenarios. The ESF (Edge-Spatial informationFusion) module realizes edge enhancement and spatial awareness to suppress background interference.The DSFF (Dynamic Sequence Feature Fusion) module efficiently integrates deep semantic featuresand shallow detail information to strengthen the detection capability for small targets. Experimentalresults demonstrate that the MSED-YOLOv8 algorithm achieves average accuracy improvementsof 7.9%, 4.2%, and 2.9% on the TT100k, CCTSDB, and GTSDB datasets, respectively, comparedwith the YOLOv8s benchmark model. Additionally, the number of parameters and the model sizeare reduced by 17.1% and 8.0%, respectively. The proposed algorithm not only enhances detectionperformance but also achieves model lightweighting, making it more suitable for traffic sign detectionin complex traffic scenes.