Method and device for identifying roadside parking behaviors based on video frames

Abstract

The embodiment of the invention provides a method and a device for identifying roadside parking behaviors based on video frames. The method comprises the following steps: acquiring a plurality of continuous video frames collected by video equipment; drawing a parking space area in a first video frame, and determining coordinate information of a parking space in the parking space area, the first video frame being any collected video frame; determining a second video frame, and performing difference calculation on the first video frame and the second video frame based on the drawn parking spacearea, the second video frame being a next video frame adjacent to the first video frame; judging whether the calculation result satisfies a predetermined detection rule, and if yes, detecting the vehicle positions in the first video frame and the second video frame through a vehicle training model based on the coordinate information of the parking space; and determining the roadside parking behavior of the vehicle based on the detection result. According to the invention, automatic management of roadside parking can be completed without identifying license plate information.

Description

technical field [0001] The invention relates to the technical field of intelligent parking management, in particular to a method and device for identifying roadside parking behavior based on video frames. Background technique [0002] On-street parking management is the parking management that utilizes the sites on both sides of the road on the ground. With the rapid development of urban economy and the continuous improvement of people's living standards, the number of urban motor vehicles has increased rapidly. Due to various reasons in history and reality, most cities are facing the problem of shortage or even serious shortage of motor vehicle parking spaces. Therefore, on-street parking management has become an important part of urban parking management, and has attracted extensive attention from the government and the public. However, since on-street parking is open parking, there are many difficulties in its management. On the one hand, manual patrols are currently use...

AI Technical Summary

Problems solved by technology

[0003] Although the on-street parking management based on high-level video does have the advantages of not being damaged after installation, comprehensive and clear captured video, and no need for human operation on site, it still needs to manually check the video information to record the entry and exit actions and license plate information. Therefore, the problem of how to automatically capture parking behaviors such as the entry and exit of vehicles has been placed in front of many practitioners

Images