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

Dynamic calibration method for roadside sensor, and medium

A dynamic calibration and sensor technology, applied in the field of sensor calibration, can solve the problems of a single sensor, time-consuming, cumbersome labeling process, etc., and achieve the effect of reducing systematic errors, coherent data collection, and ensuring accuracy.

Pending Publication Date: 2022-01-11
上海智能网联汽车技术中心有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] For the calibration of sensors installed on self-driving vehicles, the existing algorithm requires technicians to manually collect and label data. The labeling process is cumbersome and requires a high level of operator skills; It is necessary to keep the static state of the calibration position during data processing, which leads to incoherent and time-consuming data collection; the overall efficiency of the calibration process is low; and most of the existing algorithms are only suitable for a single sensor or two types of sensors, and cannot be applied to There is still room for improvement in the calibration of roadside sensors

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
  • Dynamic calibration method for roadside sensor, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0015] According to one or more embodiments, a method for dynamic calibration of roadside sensors is disclosed, such as figure 1 mentioned, including the following steps:

[0016] S1. Receive the raw data collected by each sensor, including camera image data obtained through the camera, the laser radar point cloud obtained through the laser radar, the millimeter wave radar point cloud obtained through the 4D millimeter wave radar collection, and the integrated navigation. Combined navigation information.

[0017] Among them, the integrated navigation needs to be installed on the calibration target and fixedly connected with the calibration target. For data collection by cameras, lidars, and 4D millimeter-wave radars, it is necessary to calibrate the target and collect data when the positioning signal is judged to be good according to the set standards and m...

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 dynamic calibration method for a roadside sensor. The dynamic calibration method solves the defects that the calibration of an existing algorithm is difficult to automatically, coherently and efficiently complete and cannot be applied to the calibration of the roadside sensor, and is characterized in that time synchronization is carried out on the received original data of each sensor, then the original data are respectively processed to obtain coordinates of calibration feature points, error data in the coordinates is eliminated, each sensor is calibrated by utilizing effective calibration data, a calibration result is stored and a calibration effect is verified. The dynamic calibration method for the roadside sensor can be used for simultaneously carrying out joint automatic calibration processing on multiple sensors, reducing systematic errors, and improving calibration accuracy.

Description

technical field [0001] The invention relates to sensor calibration technology, in particular to a roadside sensor dynamic calibration method and medium. Background technique [0002] For the calibration of sensors installed on self-driving vehicles, the existing algorithm requires technicians to manually collect and label data. The labeling process is cumbersome and requires a high level of operator skills; It is necessary to keep the static state of the calibration position during data processing, which leads to incoherent and time-consuming data collection; the overall efficiency of the calibration process is low; and most of the existing algorithms are only suitable for a single sensor or two types of sensors, and cannot be applied to There is still room for improvement in the calibration of roadside sensors. Contents of the invention [0003] The purpose of the present invention is to provide a dynamic calibration method for roadside sensors, which can simultaneously ...

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): G01C25/00G01S7/40G06T7/80
CPCG01C25/00G01S7/40G06T7/80
Inventor 王秋原张宇超高瑞金李波张雷波
Owner 上海智能网联汽车技术中心有限公司
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