AR Head-Up Display Calibration via Camera Coordinate Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current Augmented Reality Head-Up Display (ARHUD) systems require manual adjustments and trials to superimpose projected images with real scenes, making the process complex and inefficient.

Innovation Solution

An image projection method that acquires camera coordinates and relative conversion relationships between AR camera and head-up display parameters to automatically determine and project images, eliminating the need for manual adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual adjustments and trials are used to superimpose projected images with real scenes, then the superposition accuracy can be achieved, but the operation complexity increases and efficiency decreases

Engineering Contradiction:
Improvesuperposition accuracyVSAvoidoperation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the manual mechanical adjustment process with an automated image processing system. The system uses coordinate transformation algorithms to automatically calculate the mapping relationship between camera coordinates and display coordinates, eliminating the need for manual parameter adjustments and trials while maintaining superposition accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-calibration by automatically capturing images, processing coordinates, and computing transformation parameters without human intervention. The calibration process is autonomous, with the system itself determining the optimal projection parameters through image analysis and mathematical computation.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If manual adjustments and trials are used to superimpose projected images with real scenes, then the superposition accuracy can be achieved, but the calibration time increases

Engineering Contradiction:
Improvesuperposition accuracyVSAvoidcalibration time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary coordinate transformation and parameter calculation before actual image projection. By pre-computing the mapping relationship between camera and display coordinate systems using captured images and mathematical models, the system eliminates the need for time-consuming manual trials during deployment.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The automated image processing and coordinate transformation system replaces manual adjustment processes, dramatically reducing calibration time while maintaining accuracy. The system uses algorithms to quickly compute transformation parameters from captured images without requiring repeated manual attempts.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Extent of automation

If coordinate transformation between AR camera and head-up display is implemented, then the automatic projection is achieved, but the computational complexity increases

Engineering Contradiction:
Improveautomatic projectionVSAvoidcomputational complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The patent divides the coordinate transformation process into distinct segments: capturing calibration images, extracting feature point coordinates, computing extrinsic parameters, and applying transformation. This segmentation allows each computational step to be optimized independently and simplifies the overall implementation of automatic projection.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3889908B1Image projection method, apparatus, device and storage medium
Publication Date: 2024.07.31 APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD
  • EP3889908B1 patent drawingFigure 1
  • EP3889908B1 patent drawingFigure 2~3
  • EP3889908B1 patent drawingFigure 4~5

AI summary

The present application discloses an image projection method, apparatus, device and storage medium and relates to the field of intelligent transportation, and the specific implementation thereof is: acquiring a first camera coordinate of an area to be calibrated in a camera coordinate system of an AR camera on a vehicle, where the area to be calibrated is located within a photographing range of the AR camera; acquiring a relative conversion relationship between a first extrinsic parameter matrix of the AR camera and a second extrinsic parameter matrix of a head-up display on the vehicle; determining, according to the first camera coordinate and the relative conversion relationship, a second camera coordinate of a projection symbol corresponding to the area to be calibrated in a coordinate system of the head-up display; and controlling, according to the second camera coordinate, the head-up display to project an image including the projection symbol. The real scene superposition of the projection symbol and the area to be calibrated is realized after the image is projected, the operation is simple and efficient, eliminating the need to manually adjust the parameters and repeated attempts.