Vehicle Camera Extrinsic Calibration Using Movable Body Portions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing camera calibration methods for vehicle-mounted systems are imprecise due to vehicle position changes and require precise reference points, leading to inaccurate obstacle detection in driver assistance systems.
Innovation Solution
A system and method for extrinsic calibration of image capture devices using vehicle portions like mirrors, doors, and bonnets, capturing multiple images to determine device orientation relative to vehicle axes without needing precise reference points or vehicle motion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If offline calibration method is used with targets at defined positions, then extrinsic parameters can be determined, but vehicle position changes during calibration affect the accuracy
Solution Approach 1:
The calibration method uses the vehicle's own body portions (doors, mirrors, bonnet) as reference objects instead of external targets. This self-referential approach eliminates the problem of vehicle position changes affecting calibration accuracy, as the reference objects move with the vehicle and maintain stable relative geometric relationships.
Solution Approach 2:
The calibration process is divided into capturing multiple images of different vehicle body portions (door, mirror, bonnet) in sequence. Each body portion serves as an independent reference object, and their combined geometric relationships enable accurate determination of camera extrinsic parameters without requiring the vehicle to remain in a fixed position.
2Adaptability or versatility
If online calibration method is used with moving vehicle, then calibration can be performed in real conditions, but clear reference points are required which may not be available
Solution Approach 1:
The system uses the vehicle's own body portions as reference objects, eliminating the need for external reference points like road signs or lane markings. This self-referential approach enables calibration in diverse real-world conditions without dependency on environmental features, while maintaining accurate measurement through the stable geometric relationships of vehicle components.
3Measurement precision
If multiple reference points are used for calibration, then accuracy can be improved, but setup time and complexity increase
Solution Approach 1:
The vehicle's body portions (door, mirror, bonnet) inherently serve as reference objects with known geometric relationships. This eliminates the need for manual setup of external reference targets, significantly reducing calibration setup time while maintaining accuracy through the stable and predictable geometric relationships between vehicle components.
Data Source
Figure 1
Figure 2~4
Figure 5~6
AI summary
Disclosed are a system and a method for extrinsic calibration of an image capture system of a vehicle, the vehicle comprises a body and a body portion, wherein the body portion is configured to rotate around a rotation axis relative to the vehicle comprising an image capture system comprising an image capture device adapted to capture at least two images of the body and/or surrounding area of the vehicle, wherein the image capture device is mounted on a body portion, an identification unit adapted to identify at least two image features in the images, a calculation unit adapted to calculate a direction of the rotation axis relative to the image capture device on the basis of the image features, and a calibration unit configured to determine extrinsic parameters of the image capture system on the basis of the calculated direction of the rotation axis relative to vehicle. Using the invention, simple and fast calibration of image capture systems on vehicles is made possible using degrees of freedom of movement that the image capture system possess due to being mounted to movable vehicle portions.