基于轻量化YOLOv4的交通信息实时检测方法  

Real-time detection method of traffic information based on lightweight YOLOv4

作　　者：郭克友[1] 李雪[1] 杨民 GUO Keyou;LI Xue;YANG Min(School of Artificial Intelligence,Beijing Technology and Business University,Beijing 100048,China)

机构地区：[1]北京工商大学人工智能学院,北京100048

出　　处：《计算机应用》2023年第1期74-80,共7页journal of Computer Applications

摘　　要：针对日常道路场景下的车辆目标检测问题,提出一种轻量化的YOLOv4交通信息实时检测方法。首先,制作了一个多场景、多时段的车辆目标数据集,并利用K-means++算法对数据集进行预处理;其次,提出轻量化YOLOv4检测模型,利用MobileNet-v3替换YOLOv4的主干网络,降低模型的参数量,并引入深度可分离卷积代替原网络中的标准卷积;最后,结合标签平滑和退火余弦算法,使用LeakyReLU激活函数代替MobileNet-v3浅层网络中原有的激活函数,从而优化模型的收敛效果。实验结果表明,轻量化YOLOv4的权值文件为56.4 MB,检测速率为85.6 FPS,检测精度为93.35%,表明所提方法可以为实际道路中的交通实时信息检测及其应用提供参考。Aiming at the problem of vehicle objection detection in daily road scenes,a real-time detection method of traffic information based on lightweight YOLOv4(You Only Look Once version 4)was proposed.Firstly,a multi-scene and multi-period vehicle object dataset was constructed,which was preprocessed by K-means++algorithm.Secondly,a lightweight YOLOv4 detection model was proposed,in which the backbone network was replaced by MobileNet-v3 to reduce the number of parameters of the model,and the depth separable convolution was introduced to replace the standard convolution in the original network.Finally,combined with label smoothing and annealing cosine algorithms,the activation function Leaky Rectified Linear Unit(LeakyReLU)was used to replace the original activation function in the shallow network of MobileNet-v3 in order to optimize the convergence effect of the model.Experimental results show that the lightweight YOLOv4 has the weight file of 56.4 MB,the detection rate of 85.6 FPS(Frames Per Second),and the detection precision of 93.35%,verifying that the proposed method can provide the reference for the real-time traffic information detection and its applications in real road scenes.

关 键 词：目标检测 深度学习 图像处理 轻量化 YOLOv4 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]