Parking space detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a parking space detection method and apparatus, an electronic device and a storage medium. The method comprises steps of obtaining a look-around image of a surrounding environment of a target vehicle; inputting the look-around image into a pre-trained neural network model to obtain an attribute heat map corresponding to the parking space in the look-around image; and processing the attribute heat map, and determining a parking space detection result in the surrounding environment based on a processing result. The method is advantaged in that a look-around image is inputted into the pre-trained neural network model, an attribute heat map corresponding to the parking space in the look-around image is obtained, a parking space detection result in the surrounding environment is determined based on a result of processing the attribute heat map, compared with the scheme of directly inputting the look-around image into the neural network model in the prior art, parkingspace detection accuracy can be improved based on the heat map characteristics of the look-around image, the training requirement for the neural network model can be reduced, and parking space detection efficiency can be improved.

Description

Technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a parking space detection method, device, electronic equipment and storage medium. Background technique [0002] In the related art, the detection of parking spaces can be realized based on deep learning. For example, images of the surrounding environment of the vehicle can be collected, and the images can be directly input into a trained neural network model for parking space detection. [0003] However, in the above technical solution, since the acquired images are directly input to the trained neural network model, this requires high training of the neural network model, otherwise it will affect the accuracy and detection efficiency of parking space detection. Summary of the invention [0004] In view of this, the present invention provides a parking space detection method, device, electronic equipment, and storage medium to solve the above technical problems. [0005...

AI Technical Summary

Problems solved by technology

[0003] However, in the above-mentioned technical solution, since the acquired images are directly input into the trained neural network model, the training requirements for the neural network model are very high, otherwise the accuracy and detection efficiency of parking space detection will be affected.

Images