Vehicle Glazing Distortion Mapping for ADAS Sensor Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle glazing systems suffer from optical distortions due to manufacturing processes, which affect the accuracy of information acquisition systems like ADAS, making it difficult to select suitable systems and calibrate them effectively, especially for semi-autonomous vehicles that rely on high-resolution image quality.
Innovation Solution
A method and system that determine and correct optical distortions in vehicle glazing by analyzing optical characteristics, generating digitized distortion information, and associating it with unique identification codes, allowing for the selection and calibration of compatible information acquisition systems through a cloud-based network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If optical distortion correction is performed using a single calibration pattern, then the calibration process is simple, but the measurement precision is insufficient because each vehicle glazing has different optical distortion patterns
Solution Approach 1:
The calibration process is divided into multiple steps: first capturing an image without the vehicle glazing to establish a reference, then capturing an image with the vehicle glazing in place. By segmenting the calibration into these distinct phases, the system can isolate and measure the specific optical distortion introduced by each glazing without requiring a completely different calibration approach for each unit.
Solution Approach 2:
The system changes the optical parameters being measured by comparing two different states: the reference state (without glazing) and the test state (with glazing). This parameter change approach allows the system to quantify the distortion introduced by the glazing itself, enabling precise measurement of each glazing's unique optical characteristics.
2Manufacturing precision
If additional glass polishing steps are performed to reduce optical distortion, then the optical quality improves, but the productivity decreases due to increased production time
Solution Approach 1:
The system uses the vehicle glazing itself as the measurement tool by capturing images through it and analyzing the optical distortion patterns. This self-service approach eliminates the need for separate, time-consuming polishing processes to achieve uniform optical quality, as each glazing's unique characteristics are measured and accounted for in the calibration process.
Solution Approach 2:
The system provides feedback about the specific optical distortion pattern of each vehicle glazing by comparing reference images with images captured through the glazing. This feedback mechanism allows the calibration system to adapt to each glazing's characteristics without requiring additional manufacturing steps to uniformize the optical properties.
3Measurement precision
If high-resolution information acquisition systems are used in semi-autonomous vehicles, then the image quality improves, but the reliability decreases due to increased sensitivity to optical distortions
Solution Approach 1:
The system performs preliminary calibration by capturing reference images and comparing them with images taken through the vehicle glazing before the information acquisition system is fully deployed. This preliminary action establishes a distortion map that can be used to correct images captured by high-resolution sensors, ensuring reliable operation from the start.
Solution Approach 2:
The system applies preliminary correction for optical distortion by establishing a calibration model that counteracts the expected distortion effects. This preliminary anti-action compensates for the glazing's optical imperfections before they can degrade the high-resolution images, maintaining reliability despite the increased sensitivity of high-resolution systems.
Data Source
AI summary
Systems and methods for providing optical distortion information of a vehicle glazing are disclosed. In one example, a method comprises obtaining and analyzing, via at least one processor of a computing device, optical characteristics of the vehicle glazing; generating digitized optical distortion information for the vehicle glazing based on analysis results; generating identification information for the vehicle glazing; and associating the digitized optical distortion information with the identification information.