Trailer Wheel Position Estimation Under Camera Occlusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing camera monitor systems for commercial trucks struggle to track the position of trailer wheels when they are at low angles, as the wheels become hidden from the camera's field of view, leading to uncertainty in their real-world position, which affects semi-automated driver assist systems and electronic stability programs.
Innovation Solution
A method that involves identifying wheel locations in images, clustering them, generating a best fit curve associating wheel position with trailer angle, and estimating the wheel position using this curve when the wheel is hidden, allowing for continuous tracking without requiring trailer parameters like height and length, and providing the estimated position to additional vehicle systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If the trailer angle is low, then the field of view coverage is improved, but the wheel visibility deteriorates
Solution Approach 1:
The system pre-establishes a best fit curve model during periods when wheels are visible (normal trailer angles). This preliminary modeling allows the system to predict wheel positions during low trailer angles when wheels become hidden, resolving the contradiction by preparing the estimation mechanism in advance.
Solution Approach 2:
The patent introduces a best fit curve as an intermediary mathematical model that relates wheel positions to trailer angles. This curve serves as a mediator that translates visible wheel position data into predictions for hidden wheel positions, enabling continuous tracking despite occlusion during low trailer angles.
2Measurement precision
If the wheel position is tracked using camera visibility, then the measurement precision is improved when visible, but the reliability deteriorates when hidden
Solution Approach 1:
The system continuously monitors wheel positions during visible periods and uses this feedback to update and refine the best fit curve model. This feedback mechanism ensures that the estimation model remains accurate and reliable even when wheels are hidden, as it is continuously calibrated with actual observed data.
Solution Approach 2:
The patent creates a mathematical copy (best fit curve) of the wheel position-trailer angle relationship. This curve copy allows the system to reproduce wheel position information even when direct visual measurement is unavailable, maintaining reliability during low trailer angles by relying on the replicated relationship model.
3Device complexity
If traditional mirror systems are used, then the device complexity is reduced, but the field of view coverage deteriorates
Solution Approach 1:
The camera monitor system performs multiple functions: it provides enhanced field of view coverage for the driver, tracks wheel positions for safety systems, and generates data for the best fit curve model. This multi-functionality justifies the increased device complexity by delivering additional value beyond what traditional mirrors could provide.
Data Source
AI summary
A method for estimating a trailer wheel position includes identifying a first set of wheel locations in a first image. Each of the wheel locations in the first set of wheel locations is associated with a corresponding trailer angle. The first set of wheel locations is clustered and a primary cluster in the first set of wheel locations is identified. A best fit curve is applied to the primary cluster. The best fit curve is a curve associating wheel position to trailer angle. An estimated wheel position is determined by applying a determined trailer angle to the best fit curve in response to the wheel being hidden in the first image. The estimated wheel position is output to at least one additional vehicle system.