Multi-Camera Vehicle Vision Calibration Using Motion Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle vision systems face challenges in accurately determining the kinematic model of vehicle motion and maintaining camera calibration, especially when detecting objects in the vehicle's path, which can lead to misalignment and inaccurate object movement prediction.
Innovation Solution
A vehicle vision system utilizing one or more CMOS cameras captures image data and determines a kinematic model based on vehicle steering angle, speed, and geometry, comparing this data with image processing to detect object movement and adjust camera calibration as needed to ensure accurate object tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If camera calibration is not continuously maintained, then system complexity is reduced, but measurement precision of object detection deteriorates
Solution Approach 1:
The system automatically performs camera calibration using detected objects and their tracked positions without requiring manual intervention. The calibration process is self-executing, using the vehicle's own motion and detected objects to recalibrate camera parameters, thus maintaining measurement precision while avoiding complex manual calibration procedures
Solution Approach 2:
The system continuously compares detected object positions with predicted positions based on vehicle motion, using this feedback to detect calibration drift and trigger automatic recalibration. This closed-loop feedback mechanism ensures measurement precision is maintained through dynamic adjustment of camera parameters based on actual performance
2Measurement precision
If multiple cameras are used for surround view, then measurement precision of object detection is improved, but device complexity increases
Solution Approach 1:
The system merges data from multiple cameras into a unified coordinate system through image stitching, creating a comprehensive surround view. By combining multiple camera feeds and processing them together with motion compensation, the system achieves enhanced detection accuracy while managing the complexity through integrated processing rather than separate independent systems
Solution Approach 2:
Each camera in the multi-camera system serves multiple functions: capturing images for surround view display, detecting objects for safety, and providing data for motion compensation and calibration. This multi-functionality reduces overall system complexity by making each component versatile rather than specialized for a single purpose
3Measurement precision
If camera calibration is adjusted frequently, then measurement precision is improved, but loss of time in system operation increases
Solution Approach 1:
Instead of performing full recalibration frequently, the system performs partial calibration adjustments only when drift is detected beyond threshold levels. This selective calibration approach maintains sufficient precision while minimizing the time lost to calibration operations by calibrating only when necessary
Data Source
AI summary
A vehicular vision system includes a plurality of cameras including a rear camera disposed at a rear portion of a vehicle and having at least a rearward field of view and a front camera disposed at a front portion of the vehicle and having at least a forward field of view. Responsive to processing at an electronic control unit of provided vehicle data, the vehicular vision system determines a vehicle motion vector during maneuvering of the vehicle. Responsive to image processing at the electronic control unit of frames of captured image data, the vehicular vision system determines an object present in the field of view of a camera of the plurality of cameras and determines movement of the object relative to the vehicle. The vehicular vision system compares the determined relative movement of the object to the determined vehicle motion vector to determine misalignment of the camera.