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

Multi-source sensor lane line determination method and system, vehicle and computer readable storage medium

A source sensor and determination method technology, applied in radio wave measurement systems, instruments, road network navigators, etc., can solve problems such as inability to evaluate, and achieve the effect of saving costs and improving robustness

Pending Publication Date: 2022-04-15
CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF22 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It cannot be used as a truth system to evaluate the achievement of other sensor lane line performance indicators

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
  • Multi-source sensor lane line determination method and system, vehicle and computer readable storage medium
  • Multi-source sensor lane line determination method and system, vehicle and computer readable storage medium
  • Multi-source sensor lane line determination method and system, vehicle and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The implementation of the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0026] like figure 1 Shown is the overall framework flow chart of the present invention. The variety of sensors can include front camera, front radar, corner radar, surround view radar, and more. The front radar, corner radar, and surround-view radar arranged around the car body collect and obtain generalized lane lines, and calculate multi-source generalized lane lines; calculate the error distribution of each source lane line and its statistical information such as the mean variance, etc. to obtain performance indicators and determine the use standards . Judging the usage scenarios and usage conditions according to the usage indicators, and performing lane line fusion.

[0027] 1. Calculation of multi-source generalized lane lines

[0028]The lane lines we are familiar with are the target-level lane line eq...

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 multi-source sensor lane line determination method, and relates to the technical field of automatic driving. A front radar, an angle radar, a look-around radar and the like arranged around a vehicle body acquire generalized lane lines, and a multi-source generalized lane line is calculated; calculating error distribution of each source lane line and statistical information such as a variance mean value to obtain a performance index, and determining a use standard; recording a difference value between each coefficient of the generalized lane line equation of each frame and the front camera, obtaining error distribution of the coefficients of the generalized lane line equation, calculating an error mean value and a variance, judging the overall performance of the sensor through the mean value and the variance, and obtaining a distribution function determination threshold value of the sensor; removing scene information such as road curvature, vehicle speed and road surface gradient distribution exceeding a threshold value, and obtaining an effective generalized lane line; and effective generalized lane lines in the multi-source sensor are fused, fusion source input is adjusted according to use conditions, and a final multi-source sensor lane line is obtained.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to the evaluation of target-level and non-target-level self-fitting lane lines output by multiple sensors and the screening of effective use scenarios. Background technique [0002] Traditional sensor performance test methods generally only evaluate hardware performance. Even if there is a target-level test plan, it only tests the current mainstream lane lines, such as guardrails and curbs. There is no extensive test method and index for performance. And it needs to build a stand to increase the cost, and the maintainability is poor. [0003] Publication number CN113591618A, title: Chinese invention patent application for estimating road shape ahead, system, vehicle and storage medium discloses a road ahead shape estimating method, system, vehicle and storage medium, including the following steps: (1) Information collection: Obtain the lane line curve equation of the curr...

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): G01C21/34G01S13/42G01S13/931G01S13/86G06V20/58
Inventor 苏威王宽
Owner CHONGQING CHANGAN AUTOMOBILE CO LTD