Traffic Sign Detection Model Based on Improved RT-DETR

作     者：WANG Yong-kang SI Zhan-jun 王永康;司占军

作者机构：College of Artificial IntelligenceTianjin University of Science and TechnologyTianjin 300457China 

出 版 物：《印刷与数字媒体技术研究》 (Printing and Digital Media Technology Study)

年 卷 期：2024年第4期

页      面：97-106,178页

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Object detection Traffic signs RT-DETR CAFMFusion 

摘      要：The correct identification of traffic signs plays an important role in automatic driving technology and road safety ***,to address the problems of misdetection and omission in traffic sign detection due to the variety of sign types,significant size differences and complex background information,an improved traffic sign detection model for RT-DETR was proposed in this ***,the HiLo attention mechanism was added to the Attention-based Intra-scale Feature Interaction,which further enhanced the feature extraction capability of the network and improved the detection efficiency on high-resolution ***,the CAFMFusion feature fusion mechanism was designed,which enabled the network to pay attention to the features in different regions in each *** on this,the model could better capture the remote dependencies and neighborhood feature correlation,improving the feature fusion capability of the ***,the MPDIoU was used as the loss function of the improved model to achieve faster convergence and more accurate regression *** experimental results on the TT100k-2021 traffic sign dataset showed that the improved model achieves the performance with a precision value of 90.2%,recall value of 88.1%and mAP@0.5 value of 91.6%,which are 4.6%,5.8%,and 4.4%better than the original RT-DETR model *** model effectively improves the problem of poor traffic sign detection and has greater practical value.