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

A dangerous scene library construction method based on natural driving data

A driving data and construction method technology, applied in the field of intelligent transportation, can solve the problem of incomplete consideration of the scene, and achieve the effect of good test results

Active Publication Date: 2019-06-28
CHINA AUTOMOTIVE ENG RES INST
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When conducting real vehicle experiments, there will also be problems with incomplete consideration of scenarios, and some extreme scenarios cannot be verified by real vehicles

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 dangerous scene library construction method based on natural driving data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0048] Such as figure 1 As shown, the present invention discloses a method for constructing a dangerous scene library based on natural driving data; the method first extracts several parameters from the natural driving data, including but not limited to time period, visibility, the state of motion of the vehicle, and the type of the target vehicle , the target vehicle's motion state, traffic flow, road alignment and road surface dry conditions, etc. These parameters are used as cluster analysis indicators. The cophenet function is 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
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a dangerous scene library construction method based on natural driving data, and the method comprises the steps: firstly, selecting a plurality of parameters from the natural driving data, and enabling the parameters to serve as clustering analysis indexes; calculating the correlation between the clustering tree information and the distance of the original data by using a cophenet function, and selecting the most suitable clustering method; clustering the samples according to the selected clustering method, and determining the number of clusters; re-clustering by adopting a K-means clustering method, and introducing a contour value to judge the clustering quality, secondly, subjecting the clustering result to chi-square inspection, obtaining a significance result through the chi-square inspection, extracting significance factors in each type of dangerous scenes, and carrying out dangerous scene reconstruction and expansion.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a method for constructing a dangerous scene library based on natural driving data. Background technique [0002] In the past ten years, automotive active safety technology represented by Advanced Driver Assistance System (ADAS) has developed rapidly, and has gradually replaced passive safety as the focus of automotive safety technology research. The system uses a variety of sensors to identify static and dynamic objects, so that drivers can detect danger as much as possible, shorten human reaction time, and reduce vehicle accidents. However, the research on the evaluation method of automobile active safety has just started. At present, there is no complete set of standards in China to verify vehicles equipped with ADAS systems. [0003] Test scenarios, driver models and test objects are the three major elements of the field test method for active safety systems. The t...

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): G06F17/50G06K9/62
Inventor 徐延海陈龙李鹏辉唐云飞李爽陈涛夏芹张强杨良义樊健民
Owner CHINA AUTOMOTIVE ENG RES INST
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