| 902 | 1 | 487 |
| 下载次数 | 被引频次 | 阅读次数 |
为精确识别复杂交通场景中实时运行的动态车辆牌照，提出了一种基于YOLOv5的动态车牌识别及残差网络优化方法。基于深度残差网络优化方法，采用飞桨Padddle-Paddle平台数据集进行网络模型训练，对车牌数据样本进行图像特征提取；运用YOLOv5模型架构提升动态车牌的识别效果。基于残差网络优化的YOLOv5动态车牌识别模型输出结果显示，对于小角度、远距离的动态车牌识别，相较于传统模型，识别效果提升15%～20%,优化效果在识别范围内随角度减小及距离增加而提升。基于YOLOv5的动态车牌识别及残差网络优化模型可以有效提升动态车牌的识别精度和识别效率，为复杂交通场景的车车交互提供技术支持。
Abstract：To accurately identify dynamic vehicle license plates in complex traffic scenes in real-time, a method of recognizing dynamic license plates and optimizing residual network is proposed based on YOLOv5. Using the deep residual network optimization method and training the network model with a large sample dataset from Paddle-Paddle platform, image features are extracted from license plate data samples. YOLOv5 model architecture is employed to enhance the performance in recognizing dynamic license plates. The results of YOLOv5 dynamic license plate recognition model optimized with residual networks show a 15% to 20% improvement in recognizing dynamic license plates at small angles and long distances, compared with traditional models. The optimization performance improves as the angle decreases and the distance increases within the recognition range. YOLOv5-based dynamic license plate recognition and residual network optimization model can effectively enhance the accuracy and efficiency of dynamic license plate recognition, providing technical support for vehicle-to-vehicle interactions in complex traffic scenarios.
[1] 胡宇晨，李秋生.基于结构化深度聚类网络的人脸表情识别研究[J].赣南师范大学学报，2023,44(6):56-63.HU Yuchen,LI Qiusheng.Research on facial expression recognition based on structured depth clustering network[J].Journal of Gannan Normal University,2023,44(6):56-63.
[2] HU Y,WANG F.Multi-Modal emotion recognition combining face image and EEG signal[J].Journal of Circuits,Systems and Computers,2023,32(7):48-55.
[3] 王瑞鹏，陈锋军，朱学岩，等.采用改进的EfficientNet识别苹果叶片病害[J].农业工程学报，2023,39(18):201-210.WANG Ruipeng,CHEN Fengjun,ZHU Xueyan,et al.Identifying apple leaf diseases using improved EfficientNet[J].Transactions of the Chinese Society of Agricultural Engineering,2023,39(18):201-210.
[4] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas,2016:770-778.DOI:10.1109/CVPR.2016.90.
[5] HU H,ZHANG Z,XIE Z,et al.Local relation networks for image recognition[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul,2019:3463-3472.
[6] GU X P,WANG M X,WANG Y T,et al.Discriminative semisupervised dictionary learning method with graph embedding and pairwise constraints for crop disease image recognition[J].Crop Protection,2024,176:106489.
[7] REZA K,GHOLAMREZA A,HADI G.A new method of facial image compression based on meta-heuristic algorithms with variable bit budget allocation[J].Signal,Image and Video Processing,2023,17(8):3923-3931.
[8] CHEN Y X,LI Y Y,ZHANG S.Research on image recognition of three Fritillaria cirrhosa species based on deep learning[J].Scientific Reports,2023,13(1):19486-19486.
[9] TEJA R B,MYTHILI D,LAXMIPRASANNA D ,et al.Deep learning feature extraction architectures for real-time face detection[J].SN Computer Science,2023,4(5):645.
[10] ZHAO H,JIA J,KOLTUN V.Exploring self-attention for image recognition[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2020:10073-10082.
[11] ZHU D,XIE T,LIU Y,et al.Optimal deployment of an equitable CAV platoonable corridor on road networks with mixed traffic flow[J].Transportation Research Part C,2023,157:104399.
[12] LI D W,ZHU F,WU J P,et al.Managing mixed traffic at signalized intersections:An adaptive signal control and CAV coordination system based on deep reinforcement learning[J].Expert Systems with Applications,2024,238:121959.
[13] LIN W,WEI H.CAV-enabled data analytics for enhancing adaptive signal control safety environment[J].Accident Analysis and Prevention,2023,192:107290.
[14] CHEN X D,LIN X,MENG Q,et al.Coordinated traffic control of urban networks with dynamic entrance holding for mixed CAV traffic[J].Transportation Research Part E,2023,178:103264.
[15] LI T F,CAO Y N,XU M,et al.Optimal intersection design and signal setting in a transportation network with mixed HVs and CAVs[J].Transportation Research Part E,2023,175:103173.
[16] ZHOU Z,LI L H,QU X,et al.An autonomous platoon formation strategy to optimize CAV car-following stability under periodic disturbance[J].Physica A:Statistical Mechanics and Its Applications,2023,626:129096.
[17] 孟奕名，曲大义，杨子奕，等.网联混合车流跟驰特性及稳态响应策略[J].青岛理工大学学报，2023,44(3):104-112.MENG Yiming,QU Dayi,YANG Ziyi,et al.Car-following characteristics and steady-state response strategy of networked hybrid traffic flow[J].Journal of Qingdao University of Technology,2023,44(3):104-112.
[18] 宋慧，曲大义，王少杰，等.考虑多车响应的网联混行车流跟驰模型及稳态分析[J].吉林大学学报(工学版),2024,54(11):3220-3230.SONG Hui,QU Dayi,WANG Shaojie,et al.Connected mixed traffic flow car-following model and stability analysis considering multiple vehicles response[J].Journal of Jilin University(Engineering and Technology Edition),2024,54(11):3220-3230.
[19] 曲大义，刘浩敏，杨子奕，等.基于车路协同的交通瓶颈路段车流动态分配机制及模型[J].吉林大学学报(工学版),2024,54(8):2187-2196.QU Dayi,LIU Haomin,YANG Ziyi,et al.Dynamic allocation mechanism and model of traffic flow in bottleneck section based on vehicle infrastructure cooperation[J].Journal of Jilin University(Engineering and Technology Edition),2024,54(8):2187-2196.
[20] 曲大义，孟奕名，王韬，等.基于分子力场的网联自主车辆跟驰安全特性及模型[J].交通运输系统工程与信息，2023,23(6):33-41.QU Dayi,MENG Yiming,WANG Tao,et al.Car-following model and safety characteristics of connected autonomous vehicle based on molecular force field[J].Journal of Transportation Systems Engineering and Information Technology,2023,23(6):33-41.
基本信息:
中图分类号:U495;TP391.41
引用信息:
[1]杨子奕,崔善柠,曲大义,等.基于YOLOv5的动态车牌识别及残差网络优化方法[J].青岛理工大学学报,2025,46(02):115-123.
基金信息:
国家自然科学基金(52272311)
2023-12-06
2023
2024-01-27
2025-01-15
2025
2
2025-04-30
2025-04-30