CN-116045960-B - Map construction optimization method and device, electronic equipment and readable storage medium

Abstract

The application discloses a map construction optimization method, a device, electronic equipment and a readable storage medium, which are applied to the technical field of data processing, wherein the map construction optimization method comprises the steps of obtaining at least two single bitmaps generated by a preset map construction algorithm according to laser data; and processing each optimized single bitmap according to the overlapping area between every two optimized single bitmaps to obtain a processing single bitmap, and combining each processing single bitmap into a target map. The application solves the technical problem of inaccurate map construction.

Inventors

• HUANG ZISHAO

Assignees

• 深圳玑之智能科技有限公司

Dates

Publication Date

20260505

Application Date

20221228

Claims (8)

1. 1. The map construction optimization method is characterized by comprising the following steps of: removing noise points of the laser data to obtain processed laser data; performing straight line fitting treatment on the treatment laser data to obtain fitting straight line points; Replacing the processing laser data according to the coordinates corresponding to the fitting straight line points to obtain target laser data; acquiring at least two single bitmaps generated by a preset mapping algorithm according to laser data; Amplifying each single bitmap by a preset multiple to obtain an amplified single bitmap; Acquiring a laser origin, and connecting the laser origin with each fitting straight line point in each amplified single bitmap to obtain a connecting line region; Removing laser data in the connecting line area to perform edge optimization on each amplified single bitmap, and reducing each amplified single bitmap by the preset multiple to obtain an optimized single bitmap; And processing each optimized single bitmap according to the overlapping area between every two optimized single bitmaps to obtain a processing single bitmap, and combining each processing single bitmap into a target map.
2. 2. The map construction optimization method as claimed in claim 1, wherein the step of processing each of the optimized single bitmaps according to an overlapping area between each of the optimized single bitmaps to obtain a processed single bitmap comprises: Screening a first single bitmap group from each optimized single bitmap; Processing the first single bitmap group according to the overlapping area between every two optimized single bitmaps in the first single bitmap group to obtain a first processing single bitmap group; Selecting a second single bitmap adjacent to the first processing single bitmap group from the optimized single bitmaps; Processing the second single bitmap according to the first single bitmap processing group to obtain a second single bitmap processing, and adding the second single bitmap processing group into the first single bitmap processing group; and returning to the step of selecting the second single bitmap adjacent to the first processing single bitmap group from the optimized single bitmaps and the subsequent step until the optimized single bitmaps are selected.
3. 3. The map construction optimization method of claim 2, wherein said step of screening the first single bitmap group in each of said optimized single bitmaps comprises: Acquiring the relative position information of the global map constructed by each optimized single bitmap in the preset mapping algorithm; And selecting a first single bitmap group of which the relative position information meets a preset relative position condition from the optimized single bitmaps.
4. 4. The map construction optimization method of claim 2, wherein the first single bitmap group comprises a first unit sub-graph and a second unit sub-graph, the first processing single bitmap group comprises a first processing unit sub-graph and a second processing unit sub-graph, The step of processing the first single bitmap group according to the overlapping area between every two optimized single bitmaps in the first single bitmap group to obtain a first processing single bitmap group comprises the following steps: Converting the first unit sub-graph into first point cloud data, and converting the second unit sub-graph into second point cloud data; Acquiring third point cloud data corresponding to the first unit subgraph and fourth point cloud data corresponding to the second unit subgraph in an overlapping area between the first unit subgraph and the second unit subgraph; Determining a third conversion relation between the second unit subgraph and the global map according to a first conversion relation between the third point cloud data and the fourth point cloud data and a second conversion relation between the first unit subgraph and the global map constructed by the preset mapping algorithm; And converting the first point cloud data into fifth point cloud data according to the second conversion relation to obtain a first processing unit subgraph, and converting the second point cloud data into sixth point cloud data according to the third conversion relation to obtain a second processing unit subgraph.
5. 5. The map construction optimization method of claim 1, wherein the step of combining each of the processing unit maps into a target map comprises: clustering and combining the processing single bitmaps to obtain a clustered map; And carrying out two-dimensional processing on the clustered map to obtain a target map.
6. 6. A map construction optimizing apparatus, characterized in that the map construction optimizing apparatus comprises: the acquisition module is used for acquiring at least two single bitmaps generated by a preset mapping algorithm according to the laser data; The optimization module is used for carrying out edge optimization on each single bitmap to obtain an optimized single bitmap; and the processing module is used for processing each optimized single bitmap according to the overlapping area between every two optimized single bitmaps to obtain a processing single bitmap, and combining each processing single bitmap into a target map.
7. 7. An electronic device, the electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the map construction optimization method of any one of claims 1 to 5.
8. 8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program for realizing a map construction optimization method, the program for realizing the map construction optimization method being executed by a processor to realize the steps of the map construction optimization method according to any one of claims 1 to 5.

Description

Map construction optimization method and device, electronic equipment and readable storage medium Technical Field The present application relates to the field of data processing technologies, and in particular, to a map construction optimization method, a map construction optimization device, an electronic device, and a readable storage medium. Background At present, a map is generally constructed by laser radar data and a preset mapping algorithm, specifically, at least two single-bitmap is constructed according to the laser data, and a target map is constructed according to the radar data and the pose corresponding to each single-bitmap. Since laser radar data may be unstable and have low resolution, a constructed target map may have a burr edge line, ghost or non-straight line, resulting in inaccurate map construction. Disclosure of Invention The application mainly aims to provide a map construction optimization method, a map construction optimization device, electronic equipment and a readable storage medium, and aims to solve the technical problem of inaccurate map construction in the prior art. In order to achieve the above object, the present application provides a map construction optimization method, which includes: acquiring at least two single bitmaps generated by a preset mapping algorithm according to laser data; performing edge optimization on each single bitmap to obtain an optimized single bitmap; And processing each optimized single bitmap according to the overlapping area between every two optimized single bitmaps to obtain a processing single bitmap, and combining each processing single bitmap into a target map. Optionally, before the step of obtaining at least two single bitmaps generated by the preset mapping algorithm according to the laser data, the method further includes: removing noise points from the laser data to obtain processed laser data; performing straight line fitting treatment on the treatment laser data to obtain fitting straight line points; And replacing the processing laser data according to the coordinates corresponding to the fitting straight line points to obtain target laser data, so that the preset mapping algorithm can generate at least two single-point maps according to the target laser data. Optionally, the step of performing edge optimization on each single bitmap to obtain an optimized single bitmap includes: Amplifying each single bitmap by a preset multiple to obtain an amplified single bitmap; Acquiring a laser origin, and connecting the laser origin with each fitting straight line point in each amplified single bitmap to obtain a connecting line region; And removing the laser data in the connecting line area to perform edge optimization on each amplified single bitmap, and reducing each amplified single bitmap by the preset multiple to obtain the optimized single bitmap. Optionally, the step of processing each optimized bitmap according to the overlapping area between every two optimized bitmaps to obtain a processed bitmap includes: Screening a first single bitmap group from each optimized unit diagram; Processing the first single bitmap group according to the overlapping area between every two optimized single bitmaps in the first single bitmap group to obtain a first processing single bitmap group; Selecting a second single bitmap adjacent to the first processing single bitmap group from the optimized single bitmaps; Processing the second single bitmap according to the first single bitmap processing group to obtain a second single bitmap processing, and adding the second single bitmap processing group into the first single bitmap processing group; and returning to the step of selecting the second single bitmap adjacent to the first processing single bitmap group from the optimized single bitmaps and the subsequent step until the optimized single bitmaps are selected. Optionally, the step of screening the first bitmap group in each optimized unit map includes: acquiring relative position information of the global map constructed by each optimization unit map in the preset mapping algorithm; and selecting a first single bitmap group of which the relative position information meets a preset relative position condition from each optimized unit diagram. Optionally, the first single bitmap group comprises a first unit sub-graph and a second unit sub-graph, the first processing single bitmap group comprises a first processing unit sub-graph and a second processing unit sub-graph, The step of processing the first single bitmap group according to the overlapping area between every two optimized single bitmaps in the first single bitmap group to obtain a first processing single bitmap group comprises the following steps: Converting the first unit sub-graph into first point cloud data, and converting the second unit sub-graph into second point cloud data; Acquiring third point cloud data corresponding to the first unit subgraph and fourth point cloud data corresp