On-road parking space management method based on unmanned aerial vehicle inspection

Abstract

The invention provides an on-road parking space management method based on unmanned aerial vehicle inspection, and relates to the technical field of on-road parking space management. The method comprises the following steps: inputting a plurality of berth images obtained by an unmanned aerial vehicle into a target vehicle detection network model to obtain a berth image containing a target vehicle and a target vehicle position; inputting a target vehicle image acquired by the unmanned aerial vehicle into a license plate segmentation network model to obtain a target license plate image; processing the target license plate image to obtain a target license plate number; if the unmanned aerial vehicle inspects and shoots that the target vehicle is not in the parking space, recording the time when the target vehicle is not in the parking space, acquiring the time when the unmanned aerial vehicle inspects and shoots the image of the target vehicle last time, calculating the mid-value of the two times, and taking the mid-value as the driving-out time; and calculating the parking fee of the target vehicle according to the driving-in time and the driving-out time. Therefore, the effect of recording and managing the vehicles on the parking spaces without manual monitoring is achieved, and the parking charging efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of on-street parking management, in particular to an on-street parking space management method based on drone inspection. Background technique [0002] With the growth of domestic car ownership, car parking spaces are becoming increasingly tight. Temporary parking spaces on urban roads have eased the difficulty of urban parking, but their parking management is facing major challenges. [0003] At present, open on-street parking management is mainly divided into manual management and traditional intelligent parking management. In manual management, the inspectors hold the PDA to enter the information of the vehicles entering the parking spaces in the management area, and charge when they leave the parking spaces. However, due to manual management of fees, the management area of ​​the toll collector is limited, and the fees are difficult to supervise, and the arrears cannot be recovered, and the labor cost of...

AI Technical Summary

Problems solved by technology

However, manual management charges have a limited management area for toll collectors, and it is difficult to supervise the charges, and the evasion of arrears cannot be recovered, and the labor cost of operation and management is high.

Traditional intelligent parking management detects vehicles by installing parking locks or geomagnetic equipment on the ground of parking spaces, and records vehicle information through high-position license plate recognition devices. Each berth needs to install vehicle detection equipment on the ground, and the construction and maintenance costs are relatively high

The existing technology cannot provide a parking management charging method with low management labor costs, less installation equipment, and low construction and operation maintenance costs

Images