Vehicle Camera Calibration Using HD Map and Satellite Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing camera calibration methods for vehicles require additional pre-calibration processes and are inaccurate, especially when the camera's position and attitude angle change during vehicle travel, particularly in dynamic environments like curved roads.

Innovation Solution

A device and method that utilize high definition maps and satellite signals to obtain attitude angle information of the vehicle and camera, enabling real-time coordinate system transformation and calibration without pre-calibration, by matching camera-captured images with the map to determine accurate position and attitude angles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a recognition pattern for correction is used to obtain camera position and attitude angle, then the camera calibration can be performed, but an additional pre-calibration process is required and changes in camera position cannot be reflected while the vehicle is traveling

Engineering Contradiction:
Improvecamera calibration accuracyVSAvoidpre-calibration process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-storing high definition map data that contains precise position and attitude angle information before vehicle travel. This allows the system to perform real-time camera calibration during travel by comparing captured images with the pre-stored map data, eliminating the need for separate pre-calibration processes while maintaining high accuracy even when camera position changes.

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If the position of the vanishing point is recognized to obtain camera attitude angle, then the process is simplified, but accuracy is degraded

Engineering Contradiction:
Improvecalibration process simplicityVSAvoidcamera attitude angle accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces high definition map data as an intermediary element that bridges the simplicity of vanishing point recognition with high precision requirements. The map data serves as a reference standard that contains accurate position and attitude angle information, allowing the system to achieve both ease of operation through image matching and high measurement precision through comparison with the authoritative map data.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If traditional camera calibration methods are used, then the calibration can be completed, but the calibration does not reflect changes in camera position and attitude angle during vehicle travel

Engineering Contradiction:
Improvecalibration validityVSAvoidreal-time adaptation to position changes
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent applies dynamics by enabling continuous, real-time camera calibration during vehicle travel rather than performing a static calibration once. The system dynamically updates camera position and attitude angle information by continuously comparing captured images with the pre-stored high definition map data, ensuring that the calibration always reflects the current camera state even as the vehicle moves and the camera position changes.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS11417018B2Device and method for calibrating camera for vehicle
Publication Date: 2022.08.16 SK TELECOM CO LTD
  • US11417018B2 patent drawing
  • US11417018B2 patent drawing
  • US11417018B2 patent drawing

AI summary

In accordance with an aspect of the present disclosure, there is provided a method of calibrating a camera for a vehicle, comprising: obtaining attitude angle information of the vehicle by using a traveling direction of the vehicle obtained based on a satellite signal, and a vertical direction from ground obtained based on a high definition map; obtaining attitude angle information of the camera mounted on the vehicle by matching an image captured by the camera to the high definition map; and obtaining coordinate system transformation information between the vehicle and the camera by using the attitude angle information of the vehicle and the attitude angle information of the camera.