A lightweight license plate detection algorithm based on deep learning

作     者：Zhu, Shuo Wang, Yu Wang, Zongyang 

作者机构：Wuxi Univ Jiangsu Prov Engn Res Ctr Integrated Circuit Relia Wuxi 214105 Peoples R China Nanjing Univ Informat Sci & Technol Sch Elect & Informat Engn Nanjing Peoples R China Jiangsu Jicui Depth Sensing Technol Res Inst Co LT Wuxi Peoples R China 

出 版 物：《IET IMAGE PROCESSING》 (IET Image Proc.)

年 卷 期：2024年第18卷第2期

页      面：403-411页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Jiangsu Province Double Innovation Talents Plan for Doctoral Candidates Wuxi Institute of Technology Talent Start-up Fund [2021r014] 

主　　题：image processing neural nets pattern recognition 

摘      要：License plate detection is an important task in Intelligent Transportation Systems (ITS) and has a wide range of applications in vehicle management, traffic control, and public safety. In order to improve the accuracy and speed of mobile recognition, an improved lightweight YOLOv5s model is proposed for license plate detection. First, an improved Stemblock network is used to replace the original Focus layer in the network, which ensures strong feature expression capability and reduces a large number of parameters to lower the computational complexity;then, an improved lightweight network, ShuffleNetv2, is used to replace the backbone network of the YOLOv5s, which makes the model lighter and ensures the detection accuracy at the same time. Then, a feature enhancement module is designed to reduce the information loss caused by the rearrangement of the backbone network channels, which facilitates the information interaction in the feature fusion process;finally, the low-, medium- and high-level features in the Shufflenetv2 network structure are fused to form the final high-level output features. Experimental results on the CCPD dataset show that compared to other methods this paper obtains better performance and faster speed in the license plate detection task, in which the average precision mean value reaches 96.6%, and can achieve a detection speed of 43.86 frame/s, and the parameter volume is reduced to 5.07 M. 1. Improved Stemblock structure to reduce the number of parameters.2. Improve Shufflunetv2 as the backbone network and reduce the number of parameters.3. The attention mechanism is added to the network to improve the detection ***