Application of improved YOLOv5s algorithm in traffic sign detection and recognition

Ainring al ihe problem of low detection and recognition accuracy of traffic signs in complex traffic scenes, a target detection and recognition method based on improved Y0L0v5s algorithm was proposed. Iterative self-organizing data analysis techniques algorithm was used for clustering analysis of TT100K data sei lo select the prior frame which was more suitable for the size of traffic signs. The new prior frame could cover ihe size of traffic signs more comprehensively and improve the detection accuracy of the model. The fealure map was upsampled to oblain a larger scale feature map, and then conlacted wilh the feature map of the backbone network to obtain a new feature map with more abundanl feature information. The new feature map was used for small target detection and recognition, which improved the accuracy of small target detection and recognition. And the difference of the widlh ratio and height ratio belween the real frame and the prior frame was used to replace the difference of the aspect ratio between the real frame and the prior frame to improve the positioning loss function, which solved the problem of penalty disappearing when the width ratio was the same but the aclual size was differenl. Experimenlal results show thal compared wilh the original YOLOv5s algorithm, the improved algorilhm can improve the mean average precision by 9. 55%, and has belter Performance in detecling and recognizing small largets. © 2024 National University of Defense Technology. All rights reserved.