Lane Display Alignment Using Cant Angle Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In-vehicle camera-based image recognition systems for driving assistance and autonomous driving face recognition errors that lead to misalignment of lane markings, and using high-definition maps for accurate display increases cost and update latency.
Innovation Solution
A display system that recognizes lane markings using an in-vehicle camera and corrects the position of road shape images based on the vehicle's cant angle estimated from internal sensors such as vehicle speed, lateral acceleration, and yaw rate, reducing the need for high-definition maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-definition maps are used to accurately display lane markings, then display accuracy is improved, but cost increases and update latency increases
Solution Approach 1:
The patent introduces cant angle estimation as an intermediary correction mechanism between the camera-based lane marking detection and the final display. By estimating the cant angle from vehicle sensor data and applying it to correct the detected lane marking positions, the system achieves high display accuracy without requiring expensive high-definition maps. The correction value based on cant angle acts as a mediator that compensates for detection errors caused by road slope.
Solution Approach 2:
The patent replaces the mechanical/system-dependent approach of using high-definition maps (which require actual measurement and mapping infrastructure) with a physics-based calculation approach. By using the equation of motion that relates vehicle dynamics (lateral acceleration, yaw rate, vehicle speed) to cant angle, the system substitutes complex infrastructure-based solutions with a simpler physics-based model that achieves the same accuracy goal.
2Measurement precision
If high-definition maps are used to accurately display lane markings, then display accuracy is improved, but update latency increases
Solution Approach 1:
The system performs self-correction by using its own vehicle sensor data (lateral acceleration, yaw rate, vehicle speed) to calculate the cant angle and apply real-time corrections to lane marking positions. This self-service approach eliminates the need for external high-definition map updates, allowing the system to maintain high display accuracy with immediate updates based on current vehicle state without relying on pre-prepared map data.
Solution Approach 2:
The patent calculates and applies cant angle corrections in advance of potential display needs by continuously monitoring vehicle dynamics and pre-computing correction values. This preliminary action ensures that when lane markings need to be displayed, they are already corrected for cant effects, eliminating update latency associated with retrieving and processing high-definition map data at the moment of display.
3Device complexity
If camera-based image recognition is used to detect lane markings, then cost is reduced, but recognition errors occur leading to misalignment
Solution Approach 1:
The patent implements a feedback mechanism where vehicle sensor data (lateral acceleration, yaw rate, vehicle speed) is continuously fed into the cant angle estimation model, and the resulting correction values are applied back to the camera-based lane marking detection results. This feedback loop compensates for recognition errors caused by road cant, allowing the system to maintain low cost while improving recognition accuracy through real-time correction based on vehicle dynamics.
Solution Approach 2:
The patent changes the parameters used for lane marking position determination by introducing cant angle as an additional correction parameter. Instead of relying solely on raw camera image recognition, the system modifies the detected positions by applying corrections based on calculated cant angle values derived from vehicle dynamics parameters (lateral acceleration, yaw rate, vehicle speed). This parameter change transforms the recognition results from potentially inaccurate to accurately aligned with actual lane markings.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Reduces misalignment of road shape images in the display while minimizing cost increases, by using internal sensors to estimate and correct the position of lane markings without relying on high-definition maps.
Implementation Method 1
uses the vehicle speed of the vehicle, the lateral acceleration of the vehicle, and the yaw rate of the vehicle for the traveling state of the vehicle, and to estimate the cant angle of the lane at the position of the vehicle, based on an equation of motion that represents the balance between lateral force involved in a turn of the vehicle, lateral force acting on the vehicle due to the cant of the lane, and lateral force corresponding to the lateral acceleration of the vehicle
Data Source
AI summary
A display system is a system that displays, on a display, a lane marking of a lane in which a vehicle travels. The display system includes: a recognition and generation section configured to recognize the lane marking, based on an image captured by a camera of the vehicle, and to generate an image for display including a road shape image disposed along the lane marking; and a display control section configured to cause the display to display the image for display. The display control section is configured to estimate a cant angle of the lane, based on a result of detection by an internal sensor that detects a traveling state of the vehicle, and to correct, by using the cant angle, a position of the road shape image in the image for display.