基于改进YOLOv5s的煤矿车辆车牌检测方法  

Detection method of vehicle license plate in coal mine based on improved YOLOv5s

作　　者：沈斌 罗晓倩[1,2] 王超 SHEN Bin;LUO Xiaoqian;WANG Chao(College of Safety Engineerung,Heilongjiang University of Science&Technology,Harbin 150022,China;Coal mine gas separation and comprehensive utilization technology innovation center,Heilongjiang University of Science&Technology,Harbin 150022,China)

机构地区：[1]黑龙江科技大学安全工程学院,哈尔滨150022 [2]黑龙江科技大学煤矿瓦斯分离与综合利用技术创新中心,哈尔滨150022

出　　处：《矿冶》2025年第1期177-184,共8页Mining And Metallurgy

基　　金：黑龙江省揭榜挂帅科技攻关项目(2021ZXJ02A03);黑龙江省“百千万”工程科技重大专项资助项目(2020ZX04A01)。

摘　　要：为提升煤矿车辆车牌检测的准确性,提出了一种基于YOLOv5s改进的检测模型。在特征融合阶段,采用加权双向特征金字塔网络(BiFPN)为每个输入特征添加可学习的权重,从而学习不同输入特征的重要性,在不同层次上加强特征融合;使用EIOU损失代替YOLOv5s网络模型CIOU损失作为边界框损失函数,将预测框和真实框的纵横比影响因子拆开,分别计算预测框和真实框的长和宽,加快网络的收敛速度;在特征提取网络中融入CBAM注意力机制,提取目标的更多相关特征信息。实验结果表明,与之前的YOLOv5s模型相比,改进后的网络模型在平均精确度(mAP)上提升了1.05%,收敛速度更快,改进后的模型能有效提高车辆车牌检测的准确率。In order to improve the accuracy of license plate detection of coal mine vehicles,an improved detection model based on YOLOv5s was proposed.In the feature fusion stage,the weighted bidirectional feature pyramid network(BiFPN)is used to add learnable weights to each input feature,so as to learn the importance of different input features and strengthen feature fusion at different levels.The EIOU loss was used to replace the CIOU loss of YOLOv5s network model as the boundary frame loss function,and the aspect ratio influence factors of the predicted frame and the real frame were separated,and the length and width of the predicted frame and the real frame were calculated respectively to accelerate the convergence speed of the network.CBAM attention mechanism is integrated into feature extraction network to extract more relevant feature information of target.The experimental results show that compared with the previous YOLOv5s model,the improved network model has improved the average accuracy(mAP)by 1.04%,and the convergence speed is faster.The improved model can effectively improve the accuracy of vehicle license plate detection.

关 键 词：车辆车牌检测 YOLOv5s BiFPN EIOU CBAM 

分 类 号：TD76[矿业工程—矿井通风与安全]