Cloud license plate automatic correcting system for multiple parking lot management systems

Abstract

A cloud license plate automatic correcting system for multiple parking lot management systems comprises a cloud server and parking lot servers, and the cloud server is provided with an automatic correction library. An automatic correcting method for the automatic correction library comprises the following steps that firstly, the parking lot servers recognize and record license plate information of vehicles entering parking lots; secondly, a recognition result is uploaded to the cloud server and is compared with the automatic correction library; thirdly, whether the license plate correction information of the vehicles exists in the automatic correction library or not is judged, and if yes, the fourth step is executed; fourthly, the license plate correcting information is returned, and the license plate information, in the cloud server and the parking lot servers, of the vehicles is synchronously corrected. According to the method, the automatic correction library is deployed on the cloud server, extra hardware equipment is not needed, and the algorithm accuracy does not depend on video recognition software; the manual correction frequency is continuously reduced through establishment of the automatic correction library, the vehicle license plate recognition efficiency is improved through data accumulation, the real-time performance of the parking lot management systems is improved, and the requirements of clients are met.

Description

technical field [0001] The invention relates to the field of intelligent parking lots, in particular to a cloud license plate automatic correction system for management of multiple parking lots. Background technique [0002] With the development of video recognition technology, the entrance and exit system of the parking lot has gradually changed from the original card access method to the video recognition method, which has greatly improved the user experience. However, the recognition rate of the video recognition itself cannot be 100%, and the recognition error of the license plate usually affects the services such as parking fee payment and notification of entering and exiting the parking lot, which brings great troubles to the parking lot and users. [0003] The current common solutions are as follows: [0004] 1. Add multiple identification sources. This solution mainly uses methods such as adding cameras to allow the same vehicle to be recognized multiple times, and...

AI Technical Summary

Problems solved by technology

But the disadvantage is that additional manpower input is required, and the effect of the operation is one-time, and there is no continuous benefit

Images