Lane Positioning via Dynamic Road Visible Region Expansion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing lane positioning methods are inaccurate in regions with drastic changes in lane line color or pattern, leading to incorrect map data and reduced accuracy in determining the target lane for a vehicle.
Innovation Solution
A lane positioning method that involves obtaining a road visible region corresponding to a target vehicle, using vehicle location status information and the road visible region to obtain local map data, and determining the target lane from the local map data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If map data is obtained using a fixed radius circle centered at the target vehicle, then the positioning method is simple and fast, but the accuracy of lane-level positioning deteriorates in regions with drastic lane line color or pattern changes
Solution Approach 1:
The patent applies dynamics by transitioning from a fixed-radius circle to a dynamic region expansion approach. The system starts with an initial region based on vehicle location and iteratively expands the region by analyzing lane line characteristics. When lane line color or pattern changes are detected, the region is adjusted to include additional areas, allowing the system to adapt to complex road conditions while maintaining positioning accuracy.
Solution Approach 2:
The patent changes the parameter of map data acquisition from a fixed geometric shape (circle with fixed radius) to a variable region that expands based on detected lane line characteristics. The system modifies the region boundaries dynamically by analyzing color and pattern changes, transforming the static acquisition parameter into an adaptive one that responds to environmental conditions.
2Quantity of substance
If the map data acquisition region is expanded to cover more areas, then the completeness of map data improves, but the complexity of processing and matching increases
Solution Approach 1:
The patent segments the map data acquisition process into multiple stages: initial region definition, lane line detection, change detection, and region expansion. By dividing the complex task of acquiring comprehensive map data in complex regions into manageable segments, the system reduces overall processing complexity while achieving complete data coverage. Each stage handles a specific aspect of the problem independently.
Solution Approach 2:
The patent performs preliminary actions by first obtaining map data within an initial region based on vehicle location before expanding to cover additional areas. This preliminary acquisition provides a baseline that simplifies subsequent processing, as the system only needs to expand and refine the region rather than process entirely new data from scratch.
3Reliability
If lane line color and pattern changes are detected to improve positioning accuracy, then the reliability of lane identification improves, but the difficulty of detecting and measuring increases
Solution Approach 1:
The patent replaces complex manual analysis of lane line characteristics with automated image processing and machine learning techniques. Instead of requiring complex algorithms to detect color and pattern changes, the system uses pre-trained models that automatically identify and analyze lane line features, simplifying the detection process while maintaining high reliability in identifying lane changes and pattern variations.
Data Source
AI summary
A lane positioning method includes: obtaining a road visible region corresponding to a target vehicle, the road visible region being related to the target vehicle and a component parameter of a photographing component installed on the target vehicle, and being a road location photographed by the photographing component; obtaining, according to vehicle location status information of the target vehicle and the road visible region, local map data associated with the target vehicle, the road visible region being located in the local map data; the local map data including at least one lane associated with the target vehicle; and determining, from the at least one lane of the local map data, a target lane to which the target vehicle belongs.