Method and device for judging roadside parking based on image and geomagnetic sensor

Abstract

The embodiment of the invention provides a method and device for judging roadside parking based on an image and a geomagnetic sensor. The method comprises the following steps: obtaining to-be-processed data in a video information database, and determining the confidence of the to-be-processed data; based on the confidence coefficient of the to-be-processed data, determining first geomagnetic information data matched with the to-be-processed data in a geomagnetic information database, and judging whether the confidence coefficient is lower than a preset confidence coefficient threshold value ornot; if so, judging whether the parking action of the to-be-processed data is consistent with the parking action of the first geomagnetic information data or not; if not, storing the first geomagnetic information data and the to-be-processed data into a to-be-audited database; and re-judging whether each data in the to-be-audited database has a parking action or not, if so, generating parking information, and storing the parking information in a parking information database. According to the invention, the geomagnetic data and the high-order video recognition data are fused, so that the parking action judgment accuracy is greatly improved.

Description

technical field [0001] The invention relates to the technical field of roadside parking, in particular to a method and device for judging roadside parking based on images and geomagnetic sensors. Background technique [0002] Urban on-street parking has always been one of the chronic problems of urban management. Problems such as chaotic billing, high supervision costs, great influence by venues and weather, and inability to complete license plate and vehicle photo evidence collection are the core pain points of current on-street parking management. At present, most of the parking spaces in the city are still managed manually. On the one hand, the manual management mode has problems such as missing charges, arbitrary charges, and billing disputes. On the other hand, it is restricted by factors such as the scope and time of supervision. Accomplish all-weather management of hundreds of meters long parking spaces. [0003] In order to solve the problems of "difficult parking, ...

AI Technical Summary

Problems solved by technology

However, only using high-level video technology to judge parking events, when the scene light is weak, or when encountering heavy rain and snowstorms, the image of the berth is not clear, or for the far-end berth, the camera field of view will become very small, resulting in a decrease in recognition accuracy. Rapid descent, and there will also be a possibility of misjudgment when there is large-scale vehicle occlusion or tree leaf occlusion

Images