Unlock instant, AI-driven research and patent intelligence for your innovation.

Matching method and device for laser positioning, equipment and storage medium

A laser positioning and matching method technology, applied in the field of image analysis, can solve the problems of slow matching speed of 3D point cloud data, high time and space complexity of the matching process, and slow matching speed

Active Publication Date: 2021-04-13
北京斯年智驾科技有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because the ICP algorithm usually needs to consider the operation of 6 degrees of freedom, that is, including the translation of 3 degrees of freedom and the rotation of 3 degrees of freedom, which makes the overall matching process more complex in time and space, so the matching speed of the algorithm is slow; at the same time Also because the ICP algorithm does not filter the 3D point cloud data, the matching accuracy of the algorithm is low due to the interference of noise in the 3D point cloud data
[0007] Therefore, enterprises urgently need a new technical solution to solve the problem of slow matching speed and low matching accuracy of 3D point cloud data based on laser positioning base map

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Matching method and device for laser positioning, equipment and storage medium
  • Matching method and device for laser positioning, equipment and storage medium
  • Matching method and device for laser positioning, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] figure 1 The flow chart of a matching method for laser positioning provided by Embodiment 1 of the present invention specifically includes the following steps:

[0038] 1100. Acquire laser point cloud data based on the laser positioning image and grid data to be matched based on the image to be matched.

[0039] Specifically, the laser positioning image around the vehicle is collected by using the laser radar, and the laser positioning image is transmitted to the server, and the server obtains the laser point cloud data based on the laser positioning image.

[0040] In addition, the server may also acquire the to-be-matched raster data corresponding to the to-be-matched image of the vehicle from a pre-established database.

[0041] 1200. Filter the laser point cloud data, and process the noise-filtered laser point cloud data according to a rasterization algorithm to obtain laser raster data.

[0042] Specifically, after the server obtains the laser point cloud data, i...

Embodiment 2

[0138] Figure 4 It is a schematic structural diagram of a matching device for laser positioning in Embodiment 2 of the present invention, and the matching device may specifically include:

[0139] The acquiring module 2100 is configured to acquire laser point cloud data based on the laser positioning image and grid data to be matched based on the image to be matched.

[0140] The rasterization module 2200 is configured to filter the laser point cloud data, and process the noise-filtered laser point cloud data according to a rasterization algorithm to obtain laser raster data.

[0141] The rotation matching module 2300 is configured to match the laser raster data and the to-be-matched raster data according to a phase correlation algorithm to obtain rotation parameters, and the rotation parameters are used to explain the laser positioning image and the to-be-matched raster data. Match the rotation relationship between images.

[0142] The translation matching module 2400 is c...

Embodiment 3

[0169] Figure 5 A schematic structural diagram of a computer device provided in Embodiment 3 of the present invention, such as Figure 5 As shown, the computer device includes a memory 3100 and a processor 3200, and the number of processors 3200 in the computer device may be one or more, Figure 5 Take a processor 3200 as an example; the memory 3100 and the processor 3200 in the device can be connected through a bus or other methods, Figure 5 Take connection via bus as an example.

[0170]The memory 3100, as a computer-readable storage medium, can be used to store software programs, computer-executable programs and modules, such as the program instructions / modules corresponding to the power adapter testing method in the embodiment of the present invention (for example, the power adapter testing device in the receiving module 3100, control module 3200, and computing module 3300). The processor 3200 executes various functional applications and data processing of the device / ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the technical field of image analysis, in particular to a matching method and device for laser positioning, equipment and a storage medium. The matching method comprises the steps of acquiring laser point cloud data based on a laser positioning image and to-be-matched raster data based on a to-be-matched image; filtering the laser point cloud data, and processing the laser point cloud data after noise filtering according to a rasterization algorithm to obtain laser raster data; matching the laser raster data with the to-be-matched raster data according to a phase correlation algorithm to obtain a rotation parameter and a translation parameter; and obtaining actual positioning data according to the rotation parameter, the translation parameter and the to-be-matched raster data. The matching process of the laser point cloud data can be quickly completed, and a high-precision matching result can be obtained.

Description

technical field [0001] The present invention relates to the technical field of image analysis, in particular to a matching method, device, equipment and storage medium for laser positioning. Background technique [0002] High-precision positioning is one of the important components of the automatic driving system. It can not only ensure that the decision-making part of the automatic driving system can smoothly plan the driving route for the vehicle by providing the position and attitude of the vehicle equipped with the automatic driving system; it can also assist Environmental perception predicts the surrounding area and helps make high-precision maps. [0003] In practical applications, the high-precision positioning module of the automatic driving system needs to achieve a centimeter-level positioning accuracy for the vehicle, and the positioning accuracy for the vehicle attitude needs to be less than 0.2°. [0004] Traditional high-precision positioning modules mostly us...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01S17/89G01S17/931G06T7/70G06T5/00G06T3/60
CPCG01S17/89G01S17/931G06T7/70G06T3/60G06T2207/10028G06T2207/20104G06T2207/20056G06T5/70
Inventor 刘鹤云
Owner 北京斯年智驾科技有限公司