摘要
针对现有的车牌检测算法在复杂环境下检测效果不佳的问题,提出一种基于深度学习的GEG-YOLOv4轻量化车牌检测模型。该模型以YOLOv4为基础框架,采用轻量级网络GhostNet作为主干网络,大幅减少了模型参数量,并融入能够避免降维且能有效捕获跨通道交互信息的ECA注意力模块,增加车牌信息的通道权重,减小复杂环境背景对车牌信息的干扰。最后,在深层网络中使用Ghost模块来代替部分普通卷积,在进一步降低模型参数量的同时更好地保留了特征图的冗余信息。在大型车牌数据集CCPD上的实验结果表明,GEG-YOLOv4模型的参数量比YOLOv4减少了约88%,AP值增加了0.09%,速度提高了约55%。相较于其他方法,该方法对于复杂环境下的车牌数据具有更好的检测性能,可以满足实际应用场景的需要。
To address the problem that existing license plate detection algorithms are ineffective in complex environments,a deep learning-based GEG-YOLOv4 lightweight license plate detection model is proposed.The model uses YOLOv4 as the basic framework and GhostNet as the backbone network to significantly reduce the number of model parameters,and incorporates an ECA attention module that can avoid dimensionality reduction and effectively capture cross-channel interaction information to in⁃crease the channel weight of license plate information and reduce the interference of license plate information from the complex environment background.Finally,the Ghost module is used to replace some of the normal convolution in the deep network,which further reduces the number of model parameters while better preserving the redundant information in the feature map.The experimental results on a large license plate dataset CCPD show that the GEG-YOLOv4 model reduces the number of parameters by about 88%,increases the AP value by 0.09%and improves the speed by about 55%compared with YOLOv4,which has bet⁃ter detection performance for license plate data in complex environments than other methods and can meet the needs of practical application scenarios.
作者
山雨
张好鹏
池静
SHAN Yu;ZHANG Hao-peng;CHI Jing(College of Information and Electrical Engineering,Hebei University of Engineering,Handan 056038,China)
出处
《计算机与现代化》
2023年第7期99-104,111,共7页
Computer and Modernization
基金
邯郸市科学技术研究与发展计划项目(21422031252)。
关键词
车牌检测
深度学习
复杂环境
轻量化
YOLOv4
license plate detection
deep learning
complex environment
lightweight
YOLOv4
作者简介
山雨(1997-),女,河北邯郸人,硕士研究生,研究方向:计算机视觉,模式识别,E-mail:shanyuaaa@163.com;张好鹏(1997-),男,河北邯郸人,硕士研究生,研究方向:计算机视觉,模式识别,E-mail:zhanghaopengyyds@163.com;通信作者:池静(1973-),女,河北邯郸人,副教授,硕士,研究方向:模式识别与图像分类,算法分析与设计,E-mail:chijing@hebeu.edu.cn。
