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

Lane-level positioning method and electronic device

A positioning method and lane-level technology, applied in the field of positioning, can solve problems that affect the accuracy and robustness of lane-level positioning, and cannot correctly detect lane lines and road edges.

Active Publication Date: 2022-08-09
宁波均联智行科技股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for the above implementation, due to pure vision or vision-based lane line detection and road edge detection, the detection results are easily affected by factors such as vehicle occlusion, ground wear, and light environment, and cannot correctly detect all lane lines and roads. edge, thus affecting the accuracy and robustness of lane-level positioning

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
  • Lane-level positioning method and electronic device
  • Lane-level positioning method and electronic device
  • Lane-level positioning method and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Specifically, refer to figure 1 As shown, the process of applying the lane-level positioning method disclosed in the embodiments of the present application to perform lane-level positioning includes:

[0044] S100, acquiring an initial road image;

[0045] The initial road image may include a single frame image, or may be a road video composed of multiple video frames. The initial road image can be captured by any image acquisition device that can capture the road, such as the vehicle's on-board camera and the roadside camera, and the image includes the lane to be detected. This application does not limit the type, quantity and installation position of the cameras. It can be considered that the more cameras and the quantity, the richer the acquired information around the vehicle body, and it is relatively easier to achieve accurate lane-level positioning.

[0046] Optionally, in order to further improve the accuracy of lane-level positioning, the initial road image ma...

Embodiment 2

[0109] Corresponding to the above-mentioned embodiment, the present application provides a lane-level positioning method, wherein in this embodiment, for the same or similar content as the above-mentioned first embodiment, reference may be made to the above-mentioned introduction, which will not be repeated in the following. like Image 6 As shown, the method includes:

[0110] 6100. Detect lane lines included in the road image, and generate a first lane detection result, where the first lane detection result includes at least one first candidate lane obtained based on the detected lane lines;

[0111] Preferably, before the above 6100, the lane-level positioning method may further include:

[0112] 6110. Detect the driving direction of at least one vehicle included in the initial road image according to a preset target detection algorithm; 6111. According to the detected driving direction and preset direction of the at least one vehicle included in the initial road image Dr...

Embodiment 3

[0126] Corresponding to Embodiment 1 and Embodiment 2, the present application provides a lane-level positioning system, wherein in this embodiment, for the same or similar content as the above-mentioned Embodiment 1 and Embodiment 2, you can refer to the above introduction, and will not be described later. Repeat. like Figure 7 As shown, the system includes: a detection module 710, configured to detect lane lines included in the road image, and generate a first lane detection result, where the first lane detection result includes at least one first lane detection result obtained based on the detected lane lines a candidate lane; the detection module 710 is further configured to detect vehicles included in the road image to generate a second lane detection result, where the second lane detection result includes at least one second candidate obtained based on the detected vehicle A lane; the generating module 720 is configured to perform deduplication processing on the first ...

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 lane-level positioning method, including: detecting lane lines included in a road image to generate a first lane detection result; detecting vehicles included in a road image to generate a second lane detection result; and the second lane detection result to perform de-duplication processing to identify and eliminate duplicate lanes to generate de-duplication results; according to the de-duplication results, determine one or more lanes included in the road image; and according to the preset numbering rules, generate a or the lane number corresponding to each lane in the multiple lanes; according to the target position in the road image, the target lane corresponding to the target position is determined, and the lane number corresponding to the target lane is determined as the target lane number; When all lane lines cannot be detected correctly under the influence of factors such as ground wear, ground wear, and light environment, the lane line detection is supplemented to effectively improve the accuracy and robustness of lane-level positioning.

Description

technical field [0001] The present application relates to the field of positioning technology, and in particular, to a lane-level positioning method and an electronic device. Background technique [0002] In order to provide accurate and convenient navigation services to the vehicle, when the vehicle is driving on the road, it is necessary to precisely locate the lane in which the lane is located. [0003] In the prior art, there are some solutions for realizing lane-level positioning. Some of these implementations obtain road feature information based on high-precision maps, and achieve lane-level localization through feature matching. However, due to the high cost of high-precision map surveying and mapping and the very limited coverage of current high-precision maps, most roads currently only have low-precision standard maps, so it is difficult and costly to implement this scheme widely. Still other implementations are pure vision solutions, relying solely on computer v...

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): G06V20/58G06F16/29
CPCG06F16/29
Inventor 胡爽
Owner 宁波均联智行科技股份有限公司