Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for detecting lane lines on pavement

A lane line detection and detection method technology, applied in the field of information detection, can solve the problems of staying, high labor cost, obvious line distortion, etc., and achieve the effect of improving integrity and accuracy and saving labor cost

Active Publication Date: 2019-04-23
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantages of this detection method are: it is difficult to draw three-dimensional lines such as lane lines on the three-dimensional point cloud, the lines are obviously distorted, it is difficult to control the accuracy, and the efficiency of manual work is low; Lane lines are missed; in addition, labor costs are high
The disadvantage of this method is that the main purpose of the current algorithms developed by academia and industry is to serve automatic driving for real-time detection of lane lines, and most of them stay at the experimental level. Cannot meet the requirements of high-precision map production

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
  • Method and device for detecting lane lines on pavement
  • Method and device for detecting lane lines on pavement
  • Method and device for detecting lane lines on pavement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] see Figure 1a , which is a flowchart of a method for detecting lane lines on a road surface provided by Embodiment 1 of the present invention. The method of the embodiment of the present invention may be executed by a device for detecting lane lines on a road surface implemented in hardware and / or software, and the implementation device is typically configured in a device capable of providing lane line detection services.

[0030] The method includes:

[0031] 110. Collect an RGB image of the road surface and a point cloud intensity map of the road surface.

[0032] In this operation, the RGB image of the road surface and the point cloud intensity map of the road surface are collected synchronously. Specifically, a device for collecting the RGB image (eg, an industrial camera) and a device (eg, a radar) for collecting the point cloud intensity map may be configured on the collecting vehicle to achieve synchronous acquisition.

[0033] The device that collects the RGB...

Embodiment approach

[0036] As an embodiment of the operation of performing lane line detection on the RGB image to obtain the image three-dimensional lane line in the RGB image, it may specifically include:

[0037] Using a deep neural network model, lane line detection is performed on the RGB image to obtain a two-dimensional lane line in the RGB image;

[0038] Perform three-dimensional projection on the two-dimensional lane lines in the RGB image to obtain the three-dimensional lane lines in the RGB image, which are used as image three-dimensional lane lines.

[0039] Wherein, the deep neural network model is obtained by learning and training sample RGB images containing marked two-dimensional lane lines.

[0040] Three-dimensional projection refers to the acquisition track recorded during the acquisition process of the RGB image and the point cloud intensity map by using the internal reference information of the device that acquires the RGB image, and the acquisition trajectory recorded durin...

Embodiment 2

[0062] see Figure 2a , is a flow chart of a method for detecting lane lines on a road provided by Embodiment 2 of the present invention. On the basis of the above-mentioned embodiments, this embodiment provides a preset lane line fusion strategy to fuse the three-dimensional lane line of the image and the three-dimensional lane line of the point cloud to obtain the three-dimensional lane line of the road surface, and output The preferred option for this operation.

[0063] The method includes:

[0064] 210. Collect an RGB image of the road surface and a point cloud intensity map of the road surface.

[0065] In this operation, the RGB image of the road surface and the point cloud intensity map of the road surface are collected synchronously. For details, refer to operation 110 in the foregoing embodiment, and details are not repeated here.

[0066] 220. Perform lane line detection on the RGB image and the point cloud intensity map respectively, to obtain image three-dimen...

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

Embodiments of the present invention provide a method and device for detecting lane lines on a road. The method includes: collecting an RGB image of the road surface and a point cloud intensity map of the road surface; respectively performing lane line detection on the RGB image and the point cloud intensity map to obtain the three-dimensional lane line and the three-dimensional lane line in the RGB image The point cloud three-dimensional lane line in the point cloud intensity map; based on the preset lane line fusion strategy, the image three-dimensional lane line and the point cloud three-dimensional lane line are fused to obtain the three-dimensional lane line of the road surface, and output . By fusing the lane line detection results of the RGB image and the lane line detection results of the point cloud intensity map, in most cases, it can effectively fight against the occlusion of the road lane lines caused by other vehicles and the wear of the road lane lines and road direction arrows. , improving the integrity and accuracy of the obtained geometric profile of the three-dimensional lane line on the pavement, and in addition, saving labor costs.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of information detection, and in particular, to a method and device for detecting lane lines on a road surface. Background technique [0002] 3D high-precision maps are the main development direction of the next generation of digital maps. They are a prerequisite for the realization of automatic driving and assisted driving, and provide the main basis for accurate positioning and correct decision-making of autonomous or assisted driving vehicles. The core problem of 3D high-precision map production focuses on the detection of lane information on the road, that is, the use of 3D digital maps to accurately reconstruct information such as lanes in the real world, and the detection technology of lane lines on the road surface emerges as the times require. [0003] At present, there are mainly two detection methods. [0004] Method 1: artificial production method. The RGB image of the road...

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): G06K9/00G01B11/24
CPCG01B11/24G06V20/588
Inventor 晏涛蒋昭炎王睿索晏阳
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products