ADAS Camera Calibration for Road Coordinate Distance Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced driver assistance systems (ADAS) face challenges in accurately identifying the locations of lane marking lines and other vehicles relative to a monitored vehicle, leading to large errors and poor user experiences due to incorrect triggering of warnings.
Innovation Solution
The method involves obtaining images using an imaging sensor on a vehicle, identifying extrinsic calibration parameters, and converting pixel coordinates to a road coordinate system to accurately determine the positions of objects and lane marking lines, allowing for precise distance calculations and vehicle control actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pixel coordinate conversion to road coordinate system is implemented, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system performs preliminary calibration to determine extrinsic parameters (rotation and translation) between the camera coordinate system and road coordinate system before actual measurement. This pre-computed transformation information is stored and reused, avoiding complex real-time calculations while maintaining high position accuracy for converting pixel coordinates to road coordinates.
2Reliability
If coordinate conversion and polynomial fitting are performed, then reliability is improved, but loss of time increases
Solution Approach 1:
The system applies polynomial fitting selectively to model lane marking lines only where necessary for accurate position determination, rather than processing all image data with the same level of complexity. This partial application of complex processing reduces overall computation time while maintaining detection accuracy for critical elements.
3Measurement precision
If extrinsic calibration parameters are used for conversion, then measurement precision is improved, but ease of manufacture worsens
Solution Approach 1:
The system performs self-calibration by automatically determining extrinsic parameters through processing images of known reference objects (such as lane markings with standard dimensions) captured during initial setup. This self-calibration process eliminates the need for manual measurement and complex calibration procedures, making the system easier to manufacture and deploy while achieving high coordinate accuracy.
Data Source
AI summary
A method includes obtaining an image of a scene using an imaging sensor on a vehicle, where the image captures at least one of: one or more objects around the vehicle or one or more lane marking lines. The method also includes identifying extrinsic calibration parameters associated with the imaging sensor. The method further includes, for a specified pixel in the image, converting a position of the specified pixel within a pixel coordinate system associated with the image to a corresponding position within a road coordinate system based on the extrinsic calibration parameters. The specified pixel represents a point in the image associated with at least one of the one or more objects or the one or more lane marking lines. In addition, the method includes identifying a distance to the point in the image based on the corresponding position of the specified pixel within the road coordinate system.