High-precision map labeling method and device, equipment and storage medium

A map and high-precision technology, applied in the computer field, can solve problems such as low efficiency of labeling work, and achieve the effect of improving work efficiency

Pending Publication Date: 2019-08-16
杭州飞步科技有限公司
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides a high-precision map labeling method, device, equipment, and

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
  • High-precision map labeling method and device, equipment and storage medium
  • High-precision map labeling method and device, equipment and storage medium
  • High-precision map labeling method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] This embodiment provides a method for labeling a high-precision map, which is used for labeling a high-precision map. The execution subject of this embodiment is a high-precision map labeling device, which can be set in a computer device. The computer equipment can be a desktop computer, a notebook computer, etc.

[0034] Such as figure 1 As shown, it is a schematic flow chart of the high-precision map labeling method provided in this embodiment, and the method includes:

[0035] Step 101, obtaining map data to be labeled.

[0036] Specifically, after the original map data is collected by the vehicle, the map data to be marked can be generated according to the original map data of the map, and the map to be marked can be established. After the map to be marked is established, the map to be marked needs to be marked, and the map data to be marked can be obtained and processed accordingly.

[0037] The map data to be labeled may be map data under radar coordinates (ie...

Embodiment 2

[0051] This embodiment provides a further supplementary description of the method provided in the first embodiment.

[0052] Such as figure 2 As shown, is a schematic flow chart of the high-precision map labeling method provided in this embodiment.

[0053] As an implementable manner, on the basis of the first embodiment above, optionally, the map data to be marked includes map data corresponding to at least one preset zoom level; correspondingly, step 102 may specifically include:

[0054] Step 1021 , according to each preset zoom level, perform hierarchical cutting processing on the map data to be marked, and obtain sub-map data at each preset zoom level.

[0055] Step 103 may specifically include:

[0056] Step 1031 , input the sub-map data at each preset zoom level into the pre-trained prediction model, and obtain target label data corresponding to the sub-map data at each preset zoom level.

[0057] Step 104 may specifically include:

[0058] According to the target ...

Embodiment 3

[0112] This embodiment provides a high-precision map labeling device, which is used to implement the method in the first embodiment above.

[0113] Such as Figure 4 As shown, is a schematic structural diagram of the high-precision map labeling device provided in this embodiment. The HD map labeling device 30 includes an acquisition module 31 , a segmentation module 32 , a prediction module 33 and a processing module 34 .

[0114] Among them, the acquisition module is used to obtain the map data to be marked; the segmentation module is used to perform image segmentation processing on the map data to be marked to obtain the sub-map data; the prediction module is used to input the sub-map data into the pre-trained prediction model, The target labeling data corresponding to each sub-map data is obtained; the processing module is used to label the map data to be marked according to each target labeling data, and obtain the labeled map data.

[0115] Regarding the apparatus in th...

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 provides a high-precision map labeling method and device, equipment and a storage medium. The method comprises: acquiring map data to be labeled; performing image segmentation processingon the to-be-labeled map data to obtain image segmentation data; inputting the image segmentation data into a pre-trained prediction model to obtain target labeling data corresponding to the image segmentation data; and according to the target labeling data, labeling the to-be-annotated map data to obtain labeled map data. The working efficiency is effectively improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a high-precision map labeling method, device, equipment, and storage medium. Background technique [0002] With the rapid development of vehicle advanced driver assistance system technology and unmanned driving technology, the requirements for map accuracy are gradually increasing. The original road-level map can no longer meet the needs of unmanned vehicles. High-precision map of road information. [0003] At present, landmarks in high-precision maps usually rely on manual auxiliary labeling. Labelers find out the corresponding street view data based on experience, and mark them against the map. The existing labeling methods need to use multiple applications to work together, and have high requirements for labelers. They need to be familiar with the marked area in order to correctly retrieve the reference street view data, and the work efficiency is low. Conte...

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): G06T11/60G06T7/11G06N3/08G06N3/04
CPCG06T7/11G06T11/60G06N3/08G06N3/045
Inventor 金帮强万信逸
Owner 杭州飞步科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap