Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system of parking space status recognition based on machine learning

A machine learning, parking space status technology, applied in the field of parking lot monitoring, can solve the problems of poor parking lot management and difficult parking, and achieve the effect of realizing parking space sharing, high recognition accuracy, and solving complexity and urban parking difficulties.

Active Publication Date: 2020-02-04
青岛串并联电子科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of difficult parking and poor management of the parking lot in the prior art, the present invention provides a machine learning-based recognition method and system for the status of parking spaces in the parking lot

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system of parking space status recognition based on machine learning
  • Method and system of parking space status recognition based on machine learning
  • Method and system of parking space status recognition based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044]In the following, the present invention will be specifically described through exemplary embodiments. It should be understood, however, that elements, structures and characteristics of one embodiment may be beneficially incorporated in other embodiments without further recitation.

[0045] see figure 1 , an embodiment of the present invention provides a machine learning-based parking space state recognition method, comprising the following steps:

[0046] S1. Determine the specific installation location of the camera according to the size information of the specific parking space in the parking lot to ensure that the camera covers all the parking spaces to be tested and meets the preset installation conditions.

[0047] S2. The camera captures images of the parking lot in real time, marks the target parking space when it is idle, when it is occupied by a vehicle, and when it is occupied by a vehicle across the parking space, and stores the marked image data.

[0048] W...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method and system for recognizing the state of a parking space in a parking lot based on machine learning. The steps of the method are: determining the specific installation position of the camera according to the size information of the specific parking space in the parking lot; taking pictures of the parking lot in real time by the camera, and detecting the target Mark the parking space and store the marked image data; in the stored image data, mark all the vehicles, learn the marked image data, establish the parking space map model, vehicle recognition model, non-vehicle object model, And continuously feed back to optimize the model; compare the established three models with the image data acquired in real time to obtain the recognition result; convert the recognition result into real-time status information of the parking space and send it to the user, and push the status information of the parking space to the user in real time. And combined with the map application to guide the user to park. The invention can guide the user to park quickly and conveniently, and is convenient for the user to park and manage the parking lot.

Description

technical field [0001] The invention belongs to the field of parking lot monitoring and relates to a parking space recognition technology, in particular to a machine learning-based parking space state recognition method and system. Background technique [0002] With the rapid development of modern transportation technology and the continuous increase of car ownership, parking is a major problem in many cities today. Especially in large parking lots where people gather, the difficulty of parking has caused great trouble to both users who need to park and the operators of the parking lot. On the one hand, the scale of the parking lot is certain, the space is limited, there are many cars but few parking spaces, and the parking spaces cannot meet the needs of users. On the other hand, users cannot park quickly after entering the parking lot, and need to flow disorderly in the parking lot to find an empty parking space, which not only wastes time, but also easily causes traffic ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G08G1/14H04N5/232
CPCG08G1/14G08G1/141H04N23/80
Inventor 牟晓东王悦队王广成
Owner 青岛串并联电子科技有限公司