Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

High-precision map crowdsourcing data quality evaluation method and system based on intelligent vehicle semantics

A technology for data quality assessment and smart cars, applied in image data processing, data processing applications, measurement devices, etc., can solve the problem of poor image and video quality, effective semantic information, large differences in perception results, map making and update effects, etc. question

Pending Publication Date: 2021-05-11
SOUTH CHINA UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the sensor accuracy of different smart cars and the external conditions (weather, light, occlusion) in the driving process are different, and their perception results of the environment are quite different, resulting in poor image and video quality and insufficient effective semantic information. , causing map production and updates to be affected

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 crowdsourcing data quality evaluation method and system based on intelligent vehicle semantics
  • High-precision map crowdsourcing data quality evaluation method and system based on intelligent vehicle semantics
  • High-precision map crowdsourcing data quality evaluation method and system based on intelligent vehicle semantics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0070] Such as figure 1 As shown, the present invention provides a high-precision map crowdsourcing data quality assessment method based on smart car semantics, and the specific process is as follows:

[0071] S1. Release the current round of map crowdsourcing task requirements, and recruit smart cars to participate in crowdsourcing; among them, the task requirements include:

[0072] Time frame, including task start time and task end time;

[0073] Spatial range, including the four coordinate points of the GPS coordinate system in the map; among them, the spatial range is divided into N independent road units according to its road topology;

[0074] The budget needs to provide remuneration to the selected smart car, and the sum of the remuneration of all smart cars is...

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 crowdsourcing data quality evaluation method and system based on intelligent vehicle semantics, and the method comprises: issuing a map crowdsourcing task demand, and recruiting intelligent vehicles to participate in crowdsourcing; obtaining perception data of the intelligent vehicle, wherein the perception data comprises an image, metadata and a semantic object set; filtering the perception data uploaded by the intelligent vehicle, wherein the perception data comprises perception data which does not conform to the space-time demand of the crowdsourcing task and a dynamic semantic object; grouping the perception data according to road units, calculating and ranking the perception data based on semantic quality, and selecting the perception data according to budget; and aggregating all the selected sensing data, calculating local crowdsourcing quality, and adjusting a next-round task demand. According to the method, crowdsourcing participants are set as intelligent vehicles with semantic output capability, and crowdsourcing quality evaluation and control are carried out by adopting an edge computing and cloud computing cooperation mode. Most invalid data can be filtered at the edge end close to a data source, and high-quality semantic data meaningful to map updating can be effectively selected.

Description

technical field [0001] The present invention relates to the technical field of urban intelligent transportation, in particular to a high-precision map crowdsourcing data quality evaluation method and system based on intelligent vehicle semantics. Background technique [0002] High-precision map is the key technology to realize unmanned driving. As a high-precision restoration of the real physical world, high-precision maps are an important service to assist unmanned vehicle driving, and play an important role in vehicle positioning, environmental perception, and control decision-making. High-precision map service has the characteristics of high update frequency, high real-time requirements, low network delay, large deployment range, and wide coverage area. However, the traditional cloud computing model has insufficient real-time performance, communication delay problems, and huge data volume, which will take up A large amount of bandwidth resources, so it is not applicable ...

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): G06Q10/06G06T7/00G06T7/11G01C25/00
CPCG06Q10/06393G06T7/00G06T7/11G01C25/00G06T2207/30168
Inventor 唐洁姚令冰
Owner SOUTH CHINA UNIV OF TECH
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
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