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

Semi-automatic point cloud method for generating lanes of horizontal curve of 3D high-definition road map

A traffic lane and semi-automatic technology, applied in two-dimensional position/channel control, motor vehicles, image enhancement, etc., to achieve the effect of reducing manual intervention, ensuring high calculation, and improving accuracy

Inactive Publication Date: 2018-11-20
厦门维斯云景信息科技有限公司
View PDF3 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, processing massive 3D point clouds is considered to be a great challenge

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
  • Semi-automatic point cloud method for generating lanes of horizontal curve of 3D high-definition road map
  • Semi-automatic point cloud method for generating lanes of horizontal curve of 3D high-definition road map
  • Semi-automatic point cloud method for generating lanes of horizontal curve of 3D high-definition road map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0074] See figure 1 , The present invention provides a semi-automatic point cloud method for generating a three-dimensional high-definition road map horizontal curve traffic lane, including the following steps:

[0075] S1, original point cloud block

[0076] The original test mobile laser scan data is divided into a series of data blocks, and the corresponding contour in each data block has a predefined width. This step is implemented through the following steps:

[0077] S11. Based on the point cloud analysis of the vehicle trajectory, the original point cloud data is divided into specified widths (B g ) Multiple data blocks, set B g Between 0.5m and 2.0m;

[0078] S12. In each data block, use a given width (P g ) Segment the corresponding contour, where P g = 0.25m.

[0079] S2, generate a pseudo scan line and determine the principal point

[0080] Each contour is gridded to generate pseudo scan lines, and then the principal point is selected in each grid cell. This step is impleme...

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 discloses a semi-automatic point cloud method for generating lanes of a horizontal curve of a 3D high-definition road map. The method comprises the following steps that S1) original cloud point data is divided into data blocks; S2) the contour is each data block is gridded, and a main point is selected from each grid unit; S3) kerb points are extracted from the original cloud point data; S4) the extracted kerb points are fit into two smooth kerbs so as to extract pavement points; S5) I DW interpolation is carried out on the pavement point to generate a GRF intensity characteristic image; S6) a road graticule is extracted, and de-noising is carried out; S7) discrete road mark points are classified; S8) the clustered curve road marks are fit to obtain lanes of a horizontal curve; and S9) the lanes are adjusted according to present knowledge. Via the method, the lanes of different curvatures can be generated from 3D point cloud for the different horizontal curves rapidly andaccurately, so that the most effective and safest lens can be designed in the horizontal curve without manual operation for an automatic driving vehicle.

Description

Technical field [0001] The invention relates to the field of unmanned car navigation, in particular to a semi-automatic point cloud method for generating a three-dimensional high-definition road map horizontal curve driving lane. Background technique [0002] In recent years, the realization of autonomous driving with unmanned driving interaction has always been an object of considerable interest in the artificial intelligence and automotive engineering circles. Autonomous vehicles rely on dynamic three-dimensional (3D) high-resolution road maps to support accurate vehicle positioning and route navigation services. Compared with traditional road maps, 3D HD road maps are used for more accurate traffic navigation, with high precision and detailed road network information. With the help of conventional navigation maps, if the traffic signs are blocked by obstacles or the car is moving fast on the highway, it is difficult for the on-board sensors to recognize the traffic signs in t...

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 Applications(China)
IPC IPC(8): G05D1/02G06T7/246
CPCG05D1/0214G05D1/0221G05D1/0236G05D1/024G05D1/0251G05D1/0276G05D1/028G06T7/246G06T2207/30256G06T2207/30241G06T2207/10028
Inventor 不公告发明人
Owner 厦门维斯云景信息科技有限公司