Camera-Based Lateral Guidance Without Global Coordinate Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for deriving control variables for lateral vehicle guidance rely on projections and mappings between image data and global coordinate systems, which can lead to accuracy losses due to transformations dependent on road shape and distance.
Innovation Solution
The method derives control variables directly from camera images without the need for projections into a global coordinate system, using native measurement space data from the camera to compare traffic lane projections with travel trajectory projections, thereby eliminating transformation-related accuracy losses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If projections and mappings between image data and global coordinate systems are used, then the control variable can be derived using standard coordinate transformation methods, but accuracy losses occur due to transformations dependent on road shape and distance
Solution Approach 1:
The patent extracts and eliminates the intermediate coordinate transformation step from the traditional processing chain. Instead of mapping image data to a global coordinate system and then deriving control variables, the method directly processes image data in its native measurement space to obtain control variables for lateral guidance, thereby removing the source of accuracy losses associated with coordinate projections
Solution Approach 2:
The patent inverts the conventional approach by not transforming images into a global coordinate system, but rather adapting the control variable derivation process to work directly with the camera's native measurement space. This inversion eliminates the need for transformations that cause accuracy degradation, particularly at increasing distances from the vehicle
2Measurement precision
If traditional projection methods are used to map traffic lane and trajectory data between coordinate systems, then the control variable derivation follows standard procedures, but accuracy losses increase in a quadratic manner with respect to distance
Solution Approach 1:
The patent removes the time-consuming coordinate transformation operations from the processing pipeline. By deriving control variables directly from image data in the camera's native measurement space, the method eliminates the computational overhead associated with projecting traffic lane markings and vehicle trajectories between coordinate systems, thereby reducing processing time while maintaining or improving accuracy
Solution Approach 2:
The patent changes the measurement space parameter from global coordinate system to the camera's native image coordinate system. This parameter change allows direct comparison and derivation of control variables without requiring transformation operations, thereby eliminating both accuracy losses and processing time associated with coordinate mappings
3Measurement precision
If coordinate system transformations are performed for deriving control variables, then the method follows conventional processing steps, but more resources are required for transformations and projections
Solution Approach 1:
The patent extracts and eliminates the computationally intensive projection and mapping operations from the processing chain. By working directly with image data in the camera's native measurement space, the method removes the need for resource-heavy coordinate transformations, thereby reducing energy consumption and computational load while maintaining derivation accuracy
Solution Approach 2:
The patent uses the image data directly as the working representation without creating transformed copies in a global coordinate system. This approach avoids the computational overhead of generating and processing multiple coordinate representations, thereby conserving computational resources while achieving the same control variable derivation goal
Data Source
AI summary
A method used for deriving a control variable for lateral guidance of a motor vehicle by means of images of at least one camera of the motor vehicle, wherein the at least one camera captures images of a roadway. A more precise and/or resource-saving derivation of the control variable, and thus lateral guidance, of the motor vehicle is achieved by projecting a traffic lane to be followed as well as a travel trajectory of the motor vehicle onto the images, and by a control variable for lateral guidance of the motor vehicle being derived by comparing the traffic lane projected onto the images with the travel trajectory projected onto the images. A motor vehicle in which the method is performed is also described.