Detection method, device, electronic equipment and storage medium of traffic signs

Abstract

Embodiments of the present invention provide a traffic sign detection method, device, electronic device, and storage medium. The method includes: acquiring a current image captured by a camera on a vehicle and current posture information of the vehicle; performing object detection on the current image to obtain Each first traffic sign in the first static object group is in the corresponding area of ​​the image plane; the image plane point cloud of the image corresponding to the first static object group is determined based on the corresponding area; based on the current pose information of the vehicle, the second static object group is obtained. The world coordinates of each second traffic sign; the image plane point cloud of at least one map corresponding to the second static object group is determined based on the world coordinates of some or all of the second traffic signs; the image plane point cloud based on the image and the image plane of each map The point cloud performs element matching; if the matching is successful, the attribute information of each target traffic sign is obtained from the map and the color information of each target traffic sign is obtained from the current image. Using this method, more accurate traffic sign information is obtained.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a detection method, device, electronic equipment and storage medium of a traffic sign during driving of an automatic driving vehicle. Background technique [0002] When an autonomous vehicle is driving on the road, it is often necessary to detect traffic signs on the road, such as traffic lights or traffic signs, to obtain their attribute information, and further perform the next driving operation based on the attribute information. [0003] At present, self-driving vehicles detect traffic signs on the road, mainly by detecting the images captured by the cameras in the vehicle to obtain their attribute information, and further carry out the next driving operation based on the attribute information. For example: Based on image processing, from the image captured by the camera, identify the traffic light and obtain its color and attribute information (including th...

AI Technical Summary

Problems solved by technology

[0004] However, since the image captured by the camera may not be clear enough during the driving of the self-driving vehicle, some information may be misrecognized during the image recognition process, which leads to inaccurate attribute information of the traffic sign obtained through image detection

Images