Panoramic Camera Extrinsic Calibration With Embedded QR Codes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing camera calibration methods for panoramic view systems in vehicles are inefficient and inaccurate due to manual distance measurements and installation errors, and the use of identical checkerboard images leads to errors and reduced efficiency in calibrating extrinsic parameters.

Innovation Solution

Employing calibration objects with embedded information, such as QR codes, to facilitate accurate detection and orientation of corner points without the need for sorting, thereby improving the efficiency and accuracy of extrinsic parameter calibration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual distance measurements and identical checkerboard images are used for calibration, then the calibration process can be completed, but the accuracy and efficiency of extrinsic parameter calibration deteriorates due to measurement errors and the need for sorting corner points

Engineering Contradiction:

Improveextrinsic parameter calibration accuracyVSAvoidcalibration time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent changes the calibration object from identical checkerboard images to calibration objects with unique embedded information (such as unique QR codes or identification patterns). This parameter change allows each calibration object to be uniquely identified, eliminating the need for corner point sorting and manual distance measurements, thereby improving both calibration accuracy and reducing calibration time

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent uses embedded information (such as QR codes or identification patterns) on calibration objects that can be automatically detected and recognized. This copying approach replaces manual measurement processes with automated image recognition, significantly reducing time loss and improving measurement precision

Inventive Principle:

Principle #26Copying

2Measurement precision

If manual distance measurements are performed for calibration, then calibration can be completed, but the ease of operation deteriorates due to the complexity and time-consuming nature of manual measurements

Engineering Contradiction:

Improvecalibration accuracyVSAvoidcalibration operation simplicity

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces the mechanical manual measurement system with an automated computer vision system. The calibration objects with embedded information are captured by cameras, and the system automatically extracts position and orientation data through image processing, eliminating manual distance measurements and significantly improving ease of operation while maintaining high precision

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The calibration objects are designed to be self-identifying through embedded information. When captured by the camera, the system can automatically determine the position and orientation of each calibration object without requiring manual intervention for measurement or identification, making the calibration process self-service and operationally simple

Inventive Principle:

Principle #25Self-service

3Productivity

If identical checkerboard images are used for calibration, then the calibration process can proceed, but reliability deteriorates due to errors from sorting corner points and manual measurements

Engineering Contradiction:

Improvecalibration efficiencyVSAvoidcalibration accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent changes the calibration object from identical checkerboard images to calibration objects with unique embedded information. This parameter change fundamentally improves reliability by enabling automatic identification and elimination of sorting errors, while also improving productivity by streamlining the calibration workflow

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The embedded information on calibration objects provides automatic feedback to the system about each object's identity and position. This feedback mechanism eliminates the need for manual measurement verification and corner point sorting, improving both reliability and productivity by creating a self-verifying calibration process

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12450778B2Method for calibrating extrinsic parameters of camera devices, vehicle-mounted device, and storage medium

Publication Date: 2025.10.21 HON HAI PRECISION INDUSTRY CO LTD

AI summary

The present application relates to a field of intelligent driving, and provides a method for calibrating extrinsic parameters of camera devices of a panoramic view system, a vehicle-mounted device, and a storage medium. The method uses the camera devices to shoot multiple preset calibration objects to obtain multiple images, the calibration objects include preset embedded information. Based on the embedded information, information is extracted from each of the multiple images to obtain calibration information of each calibration object in each captured image. Based on the calibration information and intrinsic parameters of each camera device, extrinsic parameters of each camera device are determined. The above method can improve an efficiency and an accuracy of an algorithm of calibrating the extrinsic parameters.