Smart city ground parking space image processing method based on artificial intelligence and CIM

Abstract

The invention provides a smart city ground parking space image processing method based on artificial intelligence and CIM, and the method comprises the steps: carrying out the projection transformation and image splicing of a city road image collected by a camera, and projecting the city road image to a ground plane of the city road CIM to obtain a city road panorama; cutting the urban road panorama to obtain a plurality of sub-images; sending the sub-images into a semantic segmentation network, processing the sub-images to obtain a vehicle mask, a parking space area mask and a parking space line mask, calculating an IoU between the vehicle mask and the parking space area mask and an IoU between the vehicle mask and the parking space line mask, and judging ground parking space informationbased on the IoU and a set threshold value; transmitting the ground parking space information to the CIM, carrying out the visual processing of the data through employing the Web GIS technology, and displaying the ground parking space information while carrying out the real-time imaging. The method not only can detect whether the vehicle is parked in the parking space in real time, but also can detect whether one vehicle occupies two parking spaces, thereby improving the utilization rate of the parking spaces.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and intelligent transportation, in particular to an image processing method for ground parking spaces in an intelligent city based on artificial intelligence and CIM. Background technique [0002] Nowadays, for the parking space information of ground parking spaces, the general method is manual method. Through the inspection behavior of inspection personnel, information such as irregular parking, parking space utilization rate, and parking space usage time can be obtained. Due to the time-consuming and labor-intensive and lack of real-time problems of human detection, there are generally two parking space detection methods based on computer vision proposed so far. One is to assist in judging the use of parking spaces by detecting obstacles such as ground locks. This method solves the real-time problem, but the main defect is that the placement of obstacles still requires personnel to implem...

AI Technical Summary

Problems solved by technology

Based on the time-consuming and labor-intensive and lack of real-time problems of human detection, the currently proposed parking space detection methods based on computer vision generally fall into two categories:

One is to assist in judging the use of parking spaces by detecting obstacles such as ground locks. This method solves the real-time problem, but the main defect is that the placement of obstacles still requires personnel to implement, so there is still a waste of human resources; the other is By classifying the collected images at the pixel level, it is possible to detect whether the vehicle is parked in a specified area such as a parking space, but it cannot detect whether the vehicle is parked in a specified area.

[0003] The existing detection method for vehicles crossing the parking line is to combine the obtained wheel and front information with the parking space line to judge whether the vehicle has crossed the parking line. However, in real life, the wheels and the front of the car are easily blocked by other objects, resulting in The obtained wheel and front information is inaccurate, and it is easy to get wrong judgment results

Images