计算机与现代化 ›› 2025, Vol. 0 ›› Issue (02): 94-99.doi: 10.3969/j.issn.1006-2475.2025.02.013

• 图像处理 • 上一篇    下一篇

改进YOLOv7的交通标志检测算法


  

  1. (中北大学软件学院,山西 太原 030051)
  • 出版日期:2025-02-28 发布日期:2025-02-28
  • 基金资助:
    山西省重点研发计划项目(202102020101009)

Improved Traffic Sign Detection Algorithm of YOLOv7

  1. (Software School, North University of China, Taiyuan 030051, China)
  • Online:2025-02-28 Published:2025-02-28

摘要: 针对自动驾驶中小目标交通标志像素占比小导致的错检、漏检等问题,本文提出一种基于改进YOLOv7的交通标志检测算法。首先,引入小目标检测层,删除大目标检测层,以更好地适应小目标的检测需求;其次,在主干网络中引入EMA注意力机制,提高模型对多尺度目标的特征提取能力;再次,构建ELAN-RPC模块替换原ELAN,降低网络计算量,提高网络推理速度;最后,在特征融合层引入RFE模块,更好地利用浅层特征图的细节信息,提高后续自上而下的特征融合能力。实验结果表明,改进后的YOLOv7在TT100K数据集上mAP达到89.6%,比原始算法提升了5.7个百分点,同时参数量降低了37%,达到了参数量更少、精度更高的检测效果。

关键词: 交通标志检测, YOLOv7, 注意力机制, 特征融合, 深度学习

Abstract: In view of the problems such as error detection and missing detection in the small pixel proportion of traffic signs, a traffic sign detection algorithm based on improved YOLOv7 is proposed. In YOLOv7, we introduce the small target detection layer and delete the large target detection layer to better meet the detection needs of small targets. In the backbone network, we introduce the EMA attention mechanism to improve the feature extraction capability of the model for multi-scale targets with reduced computational overhead. At the same time, ELAN-RPC module is constructed to replace the original ELAN, reduce the network calculation and improve the network reasoning speed. In addition, RFE module is introduced in the feature fusion layer to make better use of the details of the shallow feature map and improve the ability of subsequent top-down feature fusion. Experimental results show that the mAP of the improved YOLOv7 on TT100K dataset reaches 89.6%, which is 5.8 percentage points higher than that of the original algorithm, while the number of parameters is reduced by 37%, achieving the detection effect of fewer parameters and higher precision.

Key words:  , traffic sign detection; YOLOv7; attention mechanism; feature fusion; deep learning

中图分类号: