Mobile Machine Vision Calibration Using Egomotion and Scene Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driver assistance and autonomous driving systems require costly and burdensome redesigns due to changes in imaging device arrangements, leading to system unreliability and a need for flexible hardware and software adjustments.
Innovation Solution
A method and system that utilize monocular images to calculate 3D scene information, estimate ego-motion, and adjust imaging devices by matching scene features across images, allowing for automatic calibration and correction of imaging devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If imaging devices are replaced or parameters are corrected due to malfunction or movement, then detection accuracy is improved, but system complexity and adjustment burden increase
Solution Approach 1:
The system automatically detects imaging device status changes by analyzing scene feature consistency across multiple imaging devices and self-adjusts parameters without requiring external intervention or manual recalibration, making the system self-maintaining
Solution Approach 2:
The system continuously monitors scene features detected by multiple imaging devices, compares them against expected geometric relationships, and uses this feedback to automatically adjust imaging device parameters when deviations are detected
2Adaptability or versatility
If hardware and software are redesigned to accommodate changes in imaging device arrangement, then system adaptability is improved, but development cost and time increase
Solution Approach 1:
The system adapts to different imaging device arrangements by dynamically adjusting parameters such as extrinsic calibration values, field of view angles, and scene feature detection thresholds rather than requiring hardware redesign or software reconfiguration
Solution Approach 2:
The system uses a universal adjustment mechanism that works across multiple imaging device types and configurations, allowing the same software framework to accommodate various sensor arrangements without dedicated redesign for each configuration
3Measurement precision
If multiple imaging devices are used to improve scene detection, then measurement precision is improved, but device complexity and adjustment difficulty increase
Solution Approach 1:
The system automatically performs cross-device calibration by detecting scene features in images from multiple imaging devices and adjusting their parameters to ensure geometric consistency, eliminating the need for manual multi-device calibration
Solution Approach 2:
The system uses detected scene features as an intermediary reference to mediate between multiple imaging devices, using the geometric relationships of these features to automatically align and calibrate all devices in the system
Data Source
AI summary
A method for adjusting an information system of a mobile machine, the information system being configured to calculate 3D information relative to a scene in which the mobile machine is moving, the method including: acquiring at least a first image of the scene at a first time and a second image of the scene at a second time; detecting one or more scene features in the first image and the second image; matching the one or more scene features across the first image and the second image based upon detection of the one or more scene features; estimating an egomotion of the mobile machine based upon the matching of the one or more scene features across the first image and the second image; and adjusting the information system by taking into account the estimation of the egomotion of the mobile machine.