Road extraction and indexing method based on multi-sensor fusion of global and local raster images

Abstract

The invention discloses a multi-sensor fusion road extraction and indexing method based on global and local grid maps, which uses global and local grid maps for data storage and preprocessing, and obtains the real-time position and attitude of unmanned vehicles through a differential positioning system , Obtain high-precision road boundaries, lane lines, and road sign position information through the lidar point cloud related data stored in the raster image, and project them into the monocular vision image, judge the lane line type and recognize the road sign based on the deep learning method Semantic information, so as to obtain high-precision road maps with semantic information. At the same time, multiple global sections and road sets are established to achieve efficient storage and indexing.

Description

technical field [0001] The invention belongs to the technical field of automatic driving, and relates to an efficient and high-precision semantic road map construction method and a visualization method thereof. Background technique [0002] High-precision maps are of great significance in the field of autonomous driving. High-resolution maps, also known as high-resolution maps, are maps specially designed for unmanned driving. Compared with traditional maps, high-precision maps can not only provide road-level navigation information, but also provide lane-level positioning and navigation information. [0003] In the current high-precision map mapping scheme, a large number of steps such as laser point cloud conversion, splicing, labeling and indexing are required, and the process is very complicated and depends on professional technicians. This makes high-precision maps expensive, highly specialized, and inefficient to produce. In addition, in the production process of the...

AI Technical Summary

Problems solved by technology

[0003] In the current high-precision map drawing scheme, a large number of steps such as laser point cloud conversion, splicing, labeling and indexing are required, and the process is very complicated and requires professional technicians

This makes high-precision maps expensive, highly specialized, and inefficient in production

In addition, in the usual high-precision map production process, there is no original semantic information, and only manual labeling of some lane lines and road signs, etc., is inefficient and the semantic information is single

At the same time, the storage and indexing methods of the existing high-precision maps are complex, which also rely on a large amount of labor, and the analysis methods are complicated, which is not conducive to the visual display during vehicle driving

Images