Check patentability & draft patents in minutes with Patsnap Eureka AI!

Lane line detection method and device based on historical cache data and storage medium

A lane line detection and history cache technology, applied in the field of lane line detection, devices and storage media based on historical cache data, can solve problems such as lane line deviation, lane line short-term occlusion, camera overexposure, etc., to avoid shaking, ensure Accuracy, the effect of improving detection accuracy

Active Publication Date: 2020-05-08
SUZHOU ZHIJIA SCI & TECH CO LTD
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the above method, some abnormal situations or sensor abnormalities are often encountered on the actual driving road, such as unclear lane lines, strong light causes the camera to be overexposed instantaneously, rain or snow makes the camera unable to see the lane lines clearly , or the lane line is temporarily blocked by other vehicles, that is, noise is generated
In the case of noise, when abnormal data is mistaken as a new lane line, it often leads to deviation of the lane line, resulting in deviation or instability of the driving lane line
[0004] like Figure 1 to Figure 3 As shown in , the new observed lane line is noise data, and it is regarded as a normal new lane line, and will be used in the next frame, resulting in deviation of the driving reference line (current driving lane line)
However, due to the noise data that was only accidental, it disappeared in the third frame after that, causing the driving reference line to return to its original position
During the whole process, the driving reference line shakes due to the noise data, so it is dangerous to get out of the line

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
  • Lane line detection method and device based on historical cache data and storage medium
  • Lane line detection method and device based on historical cache data and storage medium
  • Lane line detection method and device based on historical cache data and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Lane line detection method based on historical cache data

[0041] Such as Figure 5 As shown, the current observed lane line information is obtained by the sensor, the current observed lane line information is compared with the historical lane line information, and the current credible lane line is determined according to the comparison result, and the current credible lane line is used to generate the current driving lane line. The lane marking refers to the left lane marking or the right lane marking of the autonomous vehicle.

[0042] Such as Figure 6 As shown, the historical lane line information includes N (multiple) historical lane line information, and the multiple historical lane line information is stored in the buffer, and the historical lane line information refers to the lane at the last moment closest to the current moment Line information, lane line information at the second closest time to the current time... until the lane line information at the Nth...

Embodiment 2

[0066] Lane line detection method based on historical cache data

[0067] In the second embodiment, the determination of the current credible lane line according to the comparison result further includes the following steps:

[0068] Judgment is made on the lane information stored in the buffer according to the sequence order until a lane line with the number of associated times T greater than the set threshold S is found, and the lane line is regarded as a trusted lane line, and the current driving lane is generated by using the lane line Wire.

[0069] In the second embodiment, N takes a value of 5, the threshold S takes a value of 3, and the threshold M S Take the value 3.

[0070] All the other are the same as embodiment one.

Embodiment 3

[0072] Lane line detection device based on historical cache data

[0073] Including a sensor, the sensor is used to obtain the current observed lane line information;

[0074] Including a buffer, the buffer is used to store historical lane line information; as Figure 6 As shown, a plurality of (N) historical lane line information is stored in the buffer, and the historical lane line information refers to the lane line information at the last moment closest to the current moment, and the lane line information at the second closest moment to the current moment ...The lane line information up to the Nth closest time to the current time, and the number of association times T and the number of consecutive unassociated times M corresponding to the lane lines are also stored.

[0075] A detection module is included, and the detection module is used to realize the method described in the first embodiment or the second embodiment. Comparing the currently observed lane line informati...

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 relates to a lane line detection method and device based on historical cache data and a storage medium. The method comprises steps of acquiring current observation lane line informationthrough a sensor, comparing the current observation lane line information with historical lane line information, determining a current credible lane line according to a comparison result, and generating a current driving lane line by utilizing the current credible lane line. According to the invention, accidental abnormal data can be prevented from being taken as a normal stable lane line, the detection accuracy of the lane line is effectively improved, and the problem that the driving reference lane line shakes due to the influence of noise data is avoided.

Description

technical field [0001] The invention relates to a lane line detection method, device and storage medium based on historical cache data. Background technique [0002] In assisted driving or automatic driving technology, traditional lane line detection is mostly based on sensors such as images for real-time lane line detection. The image recognition technology uses sensors installed on the vehicle to collect environmental data inside and outside the vehicle, and implement static and dynamic objects. recognition, combined with detection and tracking technologies, to provide more stable lane line detection results. [0003] In the above method, some abnormal situations or sensor abnormalities are often encountered on the actual driving road, such as unclear lane lines, strong light causes the camera to be overexposed instantaneously, rain or snow makes the camera unable to see the lane lines clearly , or the lane line is temporarily blocked by other vehicles, that is, noise is ...

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): G06K9/00G06K9/40
CPCG06V20/588G06V10/30
Inventor 王超江頔王文斌
Owner SUZHOU ZHIJIA SCI & TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com