Road Marking Detection with Motion-Based State Vector Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The reliability of road marking detection systems is impaired by external disturbances and noise, affecting the accuracy of automatic or semi-automatic driving functions in vehicles.
Innovation Solution
A method that generates first and second sensor datasets of road markings using environmental sensors, determines motion parameters, and uses a computing unit to create observed state vectors, predicted state vectors, and corrected state vectors to reduce errors caused by noise, thereby improving the reliability of road marking detection for driver assistance and autonomous driving.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If road marking detection is performed using environmental sensor systems, then driving automation functions can be supported, but reliability is impaired by external disturbances and noise
Solution Approach 1:
The system performs preliminary actions by generating predicted state vectors based on motion parameters and previous observed state vectors before comparing them with actual sensor data. This prediction step prepares expected road marking positions in advance, allowing the system to filter out noise and disturbances when comparing predicted versus actual observations, thereby improving detection reliability
Solution Approach 2:
The system implements feedback by continuously comparing observed state vectors with predicted state vectors and using the differences to correct the predicted positions. This closed-loop feedback mechanism allows the system to compensate for external disturbances and noise by constantly adjusting predictions based on actual sensor measurements, enhancing the reliability of road marking detection
2Measurement precision
If multiple sensor datasets are processed to improve accuracy, then detection reliability increases, but computational complexity increases
Solution Approach 1:
The system changes parameters by transforming raw sensor data into state vectors that represent road marking geometry (position, orientation, curvature). This parameter transformation simplifies the processing of multiple sensor datasets by converting complex image or point cloud data into manageable geometric parameters that can be efficiently compared and corrected using motion parameters
Data Source
AI summary
According to a method for road marking detection, a sensor datasets depicting a road marking (7) at a first and a second measurement instance are generated by an environmental sensor system (4) and a parameter characterizing a motion of the environmental sensor system (4) is determined. A first and a second observed state vector describing the road marking (17) at the first and the second measurement instance, respectively, are generated based on the sensor datasets. A predicted state vector for the second measurement instance is computed depending on the at least one motion parameter and the first observed state vector and a corrected state vector for the second measurement instance is generated depending on the predicted state vector and the second observed state vector.