A management method and device for on-street parking

Abstract

The embodiment of the present invention provides a management method and device for roadside parking, the method includes: acquiring video image information collected by multiple cameras in real time, determining a parking area in each video frame image; expanding the parking area in each video frame image, Obtain the region of interest for dense optical flow calculation of each video frame; perform dense optical flow calculation on the region of interest to obtain the motion vector direction and motion vector distance of the region of interest for each frame of image; In the statistical interval of the duration, the average value of the direction of the motion vector and the average value of the distance of the motion vector of the region of interest of each frame of the image; determine the vehicle that is suspected to have an exit / entry event in the parking area; determine whether the vehicle has an exit / entry event field events. Through the present invention, the utilization rate of the computing power of the host is greatly improved, thereby realizing the efficient and accurate analysis and processing of the parking events of the multi-pole and multi-channel video cameras.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, and in particular, to a management method and device for on-street parking. Background technique [0002] With the development of the times, urban roadside smart parking management, as an extremely important part of urban smart traffic management, has entered a period of rapid development and application. At present, the new generation of information technologies such as artificial intelligence, Internet of Things, cloud computing, and big data are developing rapidly, and AI (Artificial Intelligence, artificial intelligence) accelerates the rapid increase in computing power of computing hardware platforms, providing an important technical foundation for the deep integration of city-level roadside smart parking and artificial intelligence technology. [0003] At present, the roadside parking management technology that has been commercialized in some cities mainly includes geoma...

AI Technical Summary

Problems solved by technology

However, this management method needs to increase the distance sensor, which makes the management cost higher, and in the rainy and snowy environment, the distance accuracy measured by the distance sensor has a large error, and the anti-interference ability is poor, resulting in a greatly reduced detection accuracy.

Images