Method and device for constructing high-precision map

Abstract

The invention discloses a method and device for constructing a high-precision map, a computer readable storage medium and electronic equipment, and the method comprises the steps: obtaining a spherical imaging model of pixel coordinates and space coordinates according to at least one frame of image collected by a camera and the internal parameters of the camera; acquiring a first grayscale image corresponding to the image; acquiring a second camera pose and a map point according to the spherical imaging model, the first grayscale image and the first camera pose; and constructing a high-precision map according to the second camera pose and the map point. According to the technical scheme provided by the invention, the imaging process of the camera is represented through the spherical imaging model, and the high-precision map is constructed based on the gray scale of the image, so that the construction efficiency of the high-precision map can be effectively improved.

Description

technical field [0001] The present application relates to the technical field of electronic maps, and more specifically, to a method and device for constructing high-definition maps. Background technique [0002] High-precision maps play an important role in the positioning and planning of autonomous driving. Simultaneous Localization and Mapping (SLAM) algorithms are usually used in the construction of high-precision maps. [0003] At present, when using the SLAM algorithm to build a high-precision map, the pinhole imaging model is often used to represent the imaging process of the camera, and the imaging principle of the pinhole imaging model limits the viewing angle of the camera. Only by collecting multi-view images in the direction of motion and processing the images can a more accurate high-precision map be obtained, so the construction efficiency of high-precision maps is not high. Contents of the invention [0004] In order to solve the above-mentioned technical p...

AI Technical Summary

Problems solved by technology

[0003] At present, when using the SLAM algorithm to construct a high-precision map, the pinhole imaging model is often used to represent the imaging process of the camera, and the imaging principle of the pinhole imaging model limits the viewing angle of the camera. Only by collecting multi-view images in the direction of motion and processing the images can a more accurate high-precision map be obtained, so the construction efficiency of high-precision maps is not high

Images