基于深度学习和大数据实现的车牌智能识别抓拍系统  

Intelligent license plate recognition and capturing system based on deep learning and big data

作　　者：陈超南 邱文忠 严舒琪 詹春 CHEN Chaonan;QIU Wenzhong;YAN Shuqi;ZHAN Chun(School of Communication and Electronics,Jiangxi Science and Technology Normal University,Nanchang 330013,China)

机构地区：[1]江西科技师范大学通信与电子学院,江西南昌330013

出　　处：《长江信息通信》2022年第7期30-32,共3页Changjiang Information & Communications

基　　金：江西科技师范大学大学生创新创业训练计划项目,项目编号:202111318006,项目名称:基于深度学习和大数据的车牌智能识别抓拍系统。

摘　　要：对于车辆的激增,传统的车牌识别已经不太能满足要求。因此我们想改变传统的识别技术,提高其检测速度与精度。所以本系统主要运用于需要对车牌进行识别及记录的场所,将深度学习技术运用于Jetson Nano当中,通过这个系统将车牌信息提取出来。改善当前环境的车牌识别水平,其中软件层面运用了大量的人工智能技术,如Conv Net,TensorFlow,Fast R-CNN,残差网络等。硬件层面运用了电信方面的许多基础知识,软硬结合最终就是我们的这个智能识别系统。Forthe surge of vehicles, the traditional license plate recognition has been unable to meet the requirements. Therefore,we want to change the traditional identification technology, improve its detection speed and accuracy. So this system is mainly used in places where the license plate is recognized and recorded. The deep learning technology is used in Jetson Nano, and the license plate information is extracted by this system. Improve the current environment of license plate recognition level, which uses a lot of software level of artificial intelligence technology, such as TensorFlow, ResNet, residual network. The hardware level has used the telecommunication aspect many basic knowledge, the combination of software and hardware is our this intelligent identification system finally.

关 键 词：深度学习 计算机视觉 车牌识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]