摘要
为在复杂的城市街道背景条件下实现更为高效的交通标志小目标识别,提出了一种改进的YOLOv5s算法,通过引入卷积块注意模块(CBAM)空间通道注意力机制、自适应空间特征融合(ASFF)模块和改进检测框的损失函数进一步提升网络性能,TT100K交通标志数据集上的验证结果表明,所提出的改进算法的交通标志识别平均精度均值(mAP)达到84.5%。
To achieve more efficient detection of small traffic sign targets under complex urban street background conditions,this paper proposes an improved YOLOv5s algorithm.This enhancement is achieved by incorporating a Convolution Block Attention Module(CBAM)Spatial Channel Attention Mechanism,an Adaptive Spatial Feature Fusion(ASFF)module,and an improved loss function for detection boxes.The validation results on the TT100K traffic sign dataset demonstrate that the proposed algorithm achieves a mean Average Precision(mAP)of 84.5%in traffic sign recognition.
作者
付蓉萍
付建胜
梁旺阳
Fu Rongping;Fu Jiansheng;Liang Wangyang(Guilin University of Electronic Technology,Guilin 541000)
出处
《汽车工程师》
2025年第8期22-28,共7页
Automotive Engineer
