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

A road edge recognition method and device

A road edge and grid technology, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of slow recognition speed, high labor cost, and poor practicability, so as to improve recognition speed, reduce labor cost, and reduce the amount of calculation Effect

Active Publication Date: 2020-06-02
ALIBABA (CHINA) CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the defect of the first method is that manual recognition is used, which has low efficiency and high labor cost; the defect of the second method is that the recognition speed is slow and the practicability is poor

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
  • A road edge recognition method and device
  • A road edge recognition method and device
  • A road edge recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] See figure 1 , which shows a flow chart of the road edge recognition method provided by the present application, which may include the following steps:

[0075] Step S101: Intercept the point cloud whose height from the ground is within a preset distance range from the spatial point cloud as the point cloud to be processed. The spatial point cloud is a collection of points representing objects in the road space where the vehicle is located.

[0076] In this embodiment, the spatial point cloud is obtained by scanning objects in the road space where the vehicle is located by the vehicle-mounted device, that is, the acquisition vehicle.

[0077] Among them, since the objects in the road space where the vehicle is located include: roads, road edges (such as road guardrails, road dividers, curbs, etc.), cars, road poles and obstacles (such as bridge piers), etc., the spatial point cloud includes road A collection of points, a collection of points representing road edges, a ...

Embodiment 2

[0102] In this example, in figure 1 On the basis of the road edge recognition method shown, another road edge recognition method is extended, please refer to Figure 6 ,exist figure 1 After step S105 of the shown road edge recognition method, the following steps may also be included:

[0103] Step S106: Using the grids in the grid set except the road edge grid set and the driving track of the vehicle, data filling is performed on the road edge grid set.

[0104] figure 1 The road edge grid set obtained from steps S101 to S105 in the road recognition method shown is relatively incomplete, and it is necessary to continue to use grids and vehicles in the grid set other than the road edge grid set The driving trajectory of the road edge set is filled with data to obtain a complete set of road edge grids.

[0105] Using the grids in the grid set other than the road edge set and the angle difference between the road edge set and the vehicle's driving trajectory, data filling is ...

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 present application provides a road edge recognition method and device. The road edge recognition method includes: intercepting point clouds within a preset distance range from the ground in the spatial point cloud as point clouds to be processed; The processing point cloud is divided into multiple grids; based on the vehicle's driving trajectory, the grid on the left or right side of the vehicle's driving trajectory is detected according to the detection direction from the inside to the outside, and all the grids detected first The grid is stored in the grid set; the grids with continuous positional relationship in the grid set are divided into the same grid group; the grid group with the largest number of grids is selected as the road edge grid set. In the present application, the recognition efficiency is improved through the above methods, the labor cost is reduced, and the practicability of the road edge is improved.

Description

technical field [0001] The present application relates to the field of road edge recognition, in particular to a road edge recognition method and device. Background technique [0002] Road edge recognition can provide important data support for navigation, unmanned driving and other technologies, so the recognition of road edges is very important. [0003] The existing road edge recognition methods mainly include the following two types: the first one uses artificial recognition of the road edge, specifically to manually identify the road edge from the point cloud data of the road with the naked eye, and draw the road edge; the second The first is to use the height to identify, specifically: first use the acquisition vehicle to obtain the height of the road surface, and then determine a certain height on the outside of the road based on the height of the road surface to be the road edge. However, the defect of the first method is that manual recognition is used, which has l...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V20/588
Inventor 胡胜伟贾双成
Owner ALIBABA (CHINA) CO LTD