Dynamic Vehicle Camera Calibration Through the Windshield

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing camera calibration methods for Advanced Driver Assistance Systems (ADAS) fail to account for the influence of windshields, leading to inaccurate or incomplete calibration, especially when the optical system comprising the ADAS camera and windshield changes during driving, posing a risk of limited functionality.

Innovation Solution

A method and device for dynamically calibrating the entire optical system, including the windshield and camera, while the vehicle is moving, using a special optical model and bundle adjustment techniques to estimate parameters based on the vehicle's movement and stationary objects in the environment, eliminating the need for high-precision targets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If camera calibration is performed at the end of vehicle production with high-precision targets and special calibration devices, then calibration accuracy is improved, but device complexity and manufacturing cost increase

Engineering Contradiction:
Improvecalibration accuracyVSAvoidcalibration system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs self-calibration using naturally occurring stationary objects in the environment (buildings, trees, poles) rather than requiring external calibration equipment. The camera system automatically detects and processes these objects to determine extrinsic parameters, making the system self-sufficient for calibration purposes.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The invention extracts and removes the requirement for high-precision calibration targets and special calibration devices from the calibration process. By using naturally occurring environmental objects instead, the system eliminates the need for complex calibration equipment while maintaining calibration accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

2Ease of operation

If traditional calibration methods are used that do not account for windshield influence, then calibration process is simpler, but measurement precision deteriorates

Engineering Contradiction:
Improvecalibration process simplicityVSAvoidcalibration accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The invention merges the calibration process with normal system operation. The same image processing algorithms used for environmental detection are also used for calibration, combining two functions into one unified process. This eliminates the need for separate calibration procedures while maintaining accuracy by accounting for windshield effects.

Inventive Principle:
Principle #5Merging (Combining)

3Adaptability or versatility

If dynamic recalibration is performed while the vehicle is moving, then adaptability to changing optical conditions is improved, but loss of time and processing complexity increase

Engineering Contradiction:
Improveadaptability to optical changesVSAvoidcalibration time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The calibration process operates continuously during normal vehicle operation rather than requiring periodic stops or separate calibration sessions. The system continuously processes environmental objects to maintain accurate calibration parameters, ensuring the calibration function is performed continuously as part of normal operation.

Inventive Principle:
Principle #20Continuity of useful action

4Manufacturing precision

If high-precision calibration targets and special devices are used, then manufacturing precision is improved, but manufacturing cost increases

Engineering Contradiction:
Improvecalibration precisionVSAvoidmanufacturing cost
Core Design Contradiction:
Manufacturing precisionVSEase of manufacture

Solution Approach 1:

The invention replaces expensive, precision-manufactured calibration targets with naturally occurring, free environmental objects. Instead of investing in costly calibration equipment, the system uses readily available objects like buildings, trees, and poles that require no manufacturing or special handling.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach simplifies and enhances the calibration process, achieving accuracy comparable to traditional methods without the need for expensive equipment, reducing manufacturing and maintenance costs, and ensuring consistent ADAS system performance.

Implementation Method 1

Capturing a sequence of images from the vehicle camera, the vehicle camera imaging an area of the surroundings in front of the vehicle

Methodology Applied
Scientific EffectLight reflection: Reflection

Implementation Method 2

The windshield represents an additional optical system and significantly changes the camera's projection pattern

Methodology Applied
Scientific EffectRefraction: Refraction

Data Source

PatentEP4445334B1Dynamic auto-calibration of a vehicle camera system behind a windshield
Publication Date: 2025.09.10 AUMOVIO AUTONOMOUS MOBILITY GERMANY GMBH
  • EP4445334B1 patent drawingFigure 1
  • EP4445334B1 patent drawingFigure 2
  • EP4445334B1 patent drawingFigure 3

AI summary

The invention relates to a method and a device for the autocalibration of a vehicle camera (1; 31; 40) during travel of the vehicle (33), which can be used as a sensor system for driver assistance systems and automated driving. The vehicle camera (1; 31; 40) images a region of the surroundings (45; 46) of the vehicle (33) through a window (32; 44). The method comprises the following steps: a) providing a projection model of the vehicle camera (1; 31; 40), the projection model comprising, as parameters (θj, int, ψ), a plurality of extrinsic parameters (θj), at least one intrinsic parameter (int) of the vehicle camera (1; 31; 40) and at least one parameter (ψ) characterizing the window (32; 44), b) capturing a sequence of images on the part of the vehicle camera (1; 31; 40) during cornering (5) by the vehicle (33), c) determining a curve type on the basis of the current movement of the vehicle (33) during cornering (5) by means of a curve estimator, d) estimating the parameters taking account of - pixels in the sequence of images of stationary objects (45) in the surroundings of the vehicle (33), - the current movement of the vehicle (33) and - the determined curve type, by minimizing an error function l(sn, θm, int, ψ) indicating the deviation between pixels which correspond to stationary objects (45) in the surroundings of the vehicle and which are ascertained from the sequence of images and pixels (pij) of the stationary objects (45) which are projected by means of the projection model, e) outputting at least one of the estimated parameters (θj, ψ, int). The solution affords the advantage of a considerable simplification of test systems in the production of camera-based driver assistance systems for vehicle manufacturers and of test or calibration systems for repair workshops during exchange of camera systems or vehicle windows.