In daily life traffic signs are everywhere. The symmetry of traffic signs and their susceptibility to distortion, distance, light intensity, and other factors raises the possibility of safety risks associated with aided driving in real-world scenarios. YOLOv9, a symmetrical traffic sign detection method for complicated situations, is presented to address this issue. The approach expedites the feature extraction process and minimizes the network’s computational overhead in order to optimize the delay problem. Traffic sign detection performance is improved in complicated situations, including scale and illumination changes, while maintaining a certain level of generalization and robustness. The results of experiments conducted on the CCTSDB dataset, which includes traffic signs in intricate scenarios, demonstrate the good detection capability of the YOLOv9 algorithm. Unlike the approaches used in a previous study, YOLOv9 demonstrates superior detection capabilities with both increased speed and accuracy. Because of its precision of 98.7%, recall of 99%, and precision-recall of 98.3 mAP@0.5%, YOLOv9 has a stronger detection impact than prior algorithms, as demonstrated by the results of tests conducted in real-world settings that are extremely intricate. Consequently, the algorithm outlined in this article has the potential to tremendously improve traffic sign identification accuracy, function admirably in complicated situations, and excel at detecting tiny objects.