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

A high-precision map making method based on depth learning

A production method and deep learning technology, applied to maps/plans/charts, instruments, educational tools, etc., can solve the problems of high-precision map original information collection difficulty, high labor cost, complex production process, etc., to achieve high Automatically measure and reduce the effect of repeated manual input

Inactive Publication Date: 2019-01-15
KUANDENG (BEIJING) SCI & TECH LTD
View PDF8 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a high-precision map production method based on deep learning, which is used to solve the problems of difficult original information collection, complex production process, low degree of automation and high labor cost of existing high-precision maps

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 high-precision map making method based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] This embodiment provides a high-precision map production method based on deep learning, including: using a vision system and a positioning system to collect image information; labeling high-precision map elements and scenes in the image information; using a deep learning algorithm to train according to the image labeling results Image recognition model; measure the elements of the high-precision map according to the training results of the image recognition model; manually review the errors in the training results of the image recognition model and perform iterative optimization; automatically synthesize high-precision maps based on the optimized image recognition model.

[0022] Furthermore, visual acquisition generates high-resolution image results, which are the original production materials for high-precision map automation processes. The pure visual acquisition mode makes subsequent image annotation and machine learning highly automated. Therefore, this embodiment p...

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 high-precision map making method based on depth learning, which relates to the technical field of high-precision map making. The high-precision map making method comprises the following steps: using a vision system and a positioning system to collect image information and position information; classifying and labeling the high-precision map elements and scenes in the image information; adopting the depth learning algorithm to train the image recognition model according to the image annotation results; according to the training results of the image recognition model and the collected position information, performing the precise measurement of the elements of the high-precision map; Checking manually the errors in the training results of the image recognition model,and optimizing and the image model iteratively, which indicates the precision and automaticity of the high precision map measurement; and automatically synthesizing the high-precision maps based on the optimized image recognition model. The method can solve the problems that the original information collection of the existing high-precision map is difficult, the manufacturing process is complex,the automation degree is low, and the manual input cost is large.

Description

technical field [0001] The invention relates to the technical field of high-precision map production, in particular to a high-precision map production method based on deep learning. Background technique [0002] High-precision maps are one of the core technologies in the field of autonomous driving technology. The development of high-precision maps directly affects the safety and accuracy of autonomous driving, and is a key technical node for the implementation of autonomous driving. The core characteristics of high-precision maps are the accuracy of centimeter-level elements and the richness of elements. In order to accurately ensure the safety of autonomous driving, high-precision maps express all elements of roads and their ancillary facilities with centimeter-level precision, becoming an automatic The "eyes" of the driving car. It is precisely such high-precision and high-richness requirements that make the production process of high-precision maps a major technical pr...

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): G09B29/00
CPCG09B29/006
Inventor 孙旭高三元鞠伟平焦洁邹洋
Owner KUANDENG (BEIJING) SCI & TECH 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com