基于深度学习技术的停车场收费管理系统设计与实现  

Design and Implementation of Parking Lot Charge Management System Based on Deep Learning Technology

作　　者：张立立 张振坤 刘明钊 沙毅 ZHANG Lili;ZHANG Zhenkun;LIU Mingzhao;SHA Yi(National Computer Experimental Teaching Demonstration Center,College of Computer Science and Engineering,Northeastern University,Shenyang Liaoning 110819,China;School of Physics,Dalian University of Technology,Dalian Liaoning 116024,China)

机构地区：[1]东北大学计算机科学与工程学院,国家级计算机实验教学示范中心,辽宁沈阳110819 [2]大连理工大学物理学院,辽宁大连116024

出　　处：《电子器件》2021年第1期231-235,共5页Chinese Journal of Electron Devices

基　　金：国家自然科学基金项目(61671141);国家自然科学基金项目(61501038)。

摘　　要：停车场收费管理系统使用Python语言编写实现,能够解决进出停车场的车辆的收费管理问题。停车场管理人员通过前端界面不仅可以实时观测进入停车场的每一辆车的车型、车品牌、车牌号等信息,还可实时调用储存在后端数据库的停车场内部已停的所有车辆信息,观测停车场内已停车辆的计费情况。利用从网络资源获取的数万张车牌图片,对车牌识别的神经网络进行训练。通过测试,其车牌识别效果与管理模式均取得了良好的效果,为类似于停车场的应用情景提供了一种新的管理系统。The parking lot charge management system which can solve the charging management problem of vehicles entering and leaving the parking lot is written in Python. Through the front-end interface,the parking lot managers not only can observe the vehicle type,car brand,license plate number and other information of each car entering the parking lot in real time,but also can call all the vehicle information that has been stopped inside the parking lot stored in the back-end database in real time,observing the billing situation of stopped vehicles in the parking lot. The use of tens of thousands of license plate images acquired from network resources is to train the neural network of license plate recognition. Through testing,both the license plate recognition effect and the management mode have achieved good results,providing a new management system for the application scene which is similar to the parking lot.

关 键 词：车牌识别 深度学习 PYTHON 神经网络 数据库 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]