Parking space information generation method, device and equipment and computer readable medium

Abstract

The embodiment of the invention discloses a parking space information generation method, device and equipment and a computer readable medium. One specific embodiment of the method comprises the following steps: in response to a received parking space information generation instruction sent by a terminal of a target vehicle, executing the following parking space information generation steps: acquiring a look-around image around the target vehicle; extracting a feature map set from the look-around images, and the feature maps being used for representing feature information of the look-around images; generating a classification detection result based on the feature map set and a pre-trained classification detection model, the classification detection model being used for detecting whether there are a predetermined number of parking spaces in the look-around image; and in response to the fact that the classification detection result meets a first preset condition, generating a parking space information set based on the feature map set. According to the embodiment, the generation of parking space information is realized, automatic parking space detection and parking space tracking functions are provided, and the power consumption and computing resource requirements are reduced.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to a method, device, device, and computer-readable medium for generating parking space information. Background technique [0002] Parking space information generation is a basic technology related to automatic parking in the field of automatic driving. At present, the method related to the generation of parking space information is usually as follows: first, obtain multiple surround-view images through the vehicle-mounted surround-view camera, then preprocess the multiple surround-view images to construct a panoramic top view, and then preprocess the panoramic top view, Finally, the parking space information is generated from the preprocessed panoramic top view. [0003] However, when the above method is used to generate parking space information, the following technical problems often exist: [0004] First, it not only needs to pre-process the su...

AI Technical Summary

Problems solved by technology

[0004] First, it not only needs to pre-process the surround-view image in many aspects, but also the processing efficiency of the distorted surround-view image is low. Therefore, a specific surround-view image is required when generating parking space information, and in turn, the efficiency of parking space information generation is relatively low. low and limited

[0005] Second, because the parking space information is generated for the surrounding view images with or without parking spaces, a large amount of computing resources are required, and the computing resources of the vehicle computing equipment are limited, which to a certain extent cannot meet the needs of parking space information generation. Therefore, As a result, parking space information cannot be generated to a certain extent

Images