Signboard information acquisition method and device

Abstract

The invention discloses a signboard information acquisition method and device, and belongs to the field of terminal technologies. The signboard information acquisition method comprises the steps of performing laser scanning processing on a region containing a traffic signboard to obtain an image of the traffic signboard, a plurality of laser scanning points of the traffic signboard and point clouddata of the plurality of laser scanning points, wherein the point cloud data of each laser scanning point is used for describing the corresponding laser scanning point; performing spatial clusteringon the plurality of laser scanning points based on the point cloud data of the plurality of laser scanning points to obtain a three-dimensional point cloud structure of the traffic signboard; determining a fitting plane equation of the traffic signboard based on the three-dimensional point cloud structure; and acquiring signboard information of the traffic signboard based on the image, the three-dimensional point cloud structure and the fitting plane equation of the traffic signboard. The signboard information is obtained through acquiring the plurality of laser scanning points and the point cloud data of the traffic signboard, and thus the accuracy and the efficiency of signboard information acquisition are improved.

Description

technical field [0001] The present invention relates to the technical field of terminals, in particular to a method and device for acquiring signboard information. Background technique [0002] With the development of technology, autonomous driving technology, as a typical model of artificial intelligence, has attracted more and more attention. Among them, one of the key technologies in the realization of automatic driving technology is high-precision maps. In order to obtain high-precision maps, it is necessary to obtain the signage information of traffic signs, which is one of the important components of high-precision maps. [0003] At present, the operation of obtaining the sign information of traffic signs can be as follows: through image acquisition equipment, multiple image acquisitions are performed on the area containing traffic signs to obtain multiple images. The detection method is to detect traffic sign boards on the plurality of images. Among them, the slidin...

AI Technical Summary

Problems solved by technology

[0004] However, when the sign information of the traffic sign is obtained by the above method, due to the influence of the illumination and shooting angle in the process of obtaining multiple images including the same traffic sign, the imaging color value of the traffic sign has a large difference And there may be deformation in this image, which will affect the detection of traffic signs

In addition, when using the sliding window method to determine the position of the traffic sign in the image, the amount of calculation is large and the calculation process is complicated, resulting in low efficiency in obtaining the identification information of the traffic sign

At the same time, there may be errors in the process of detecting and calculating the traffic sign, resulting in low accuracy of the obtained 3D coordinates and affecting the subsequent application of the traffic sign

Images