Vehicle Positioning Using Reference Landmarks in Dynamic Parking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately determine vehicle positioning in dynamic environments, such as underground parking lots, due to the presence of numerous dynamic objects like people and vehicles, which complicates the estimation of position and route based on semantic road information.
Innovation Solution
A processor-implemented method that selects reference landmarks from frame images using geometric relationship information, updates positioning information by detecting candidate landmarks, and adjusts using inertial and vision sensors to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If semantic road information is used for position estimation in dynamic environments, then positioning can be achieved, but accuracy deteriorates due to numerous dynamic objects like people and vehicles
Solution Approach 1:
The patent segments the environment into static semantic road information (lanes, parking lines, signs) and dynamic objects (vehicles, pedestrians). By focusing only on static landmarks for positioning and filtering out dynamic objects, the system maintains positioning accuracy in dynamic environments. The processor selectively uses static semantic information while ignoring moving objects that would otherwise interfere with position estimation.
2Reliability
If multiple candidate landmarks are selected for positioning, then positioning information can be determined, but reliability worsens due to uncertainty in selecting the most appropriate reference landmark
Solution Approach 1:
The patent implements a feedback mechanism where the processor continuously monitors the positioning information derived from multiple candidate landmarks and selects the most reliable reference landmark based on geometric relationship quality. The system provides feedback by evaluating landmark visibility, geometric configuration, and positioning consistency, then adjusts landmark selection accordingly to maintain high positioning reliability.
Solution Approach 2:
The patent changes parameters such as landmark selection criteria, geometric relationship thresholds, and reference frame configurations based on environmental conditions. By dynamically adjusting these parameters, the system optimizes positioning reliability for different scenarios while managing the complexity of landmark selection through adaptive parameter tuning.
3Measurement precision
If geometric relationship information from multiple timepoints is used, then positioning accuracy is improved, but device complexity increases due to processing multiple frame images
Solution Approach 1:
The patent applies preliminary action by pre-processing frame images to extract semantic road information and identify candidate landmarks before positioning calculation. By preparing landmark candidates and their geometric relationships in advance, the system reduces real-time processing complexity while maintaining high positioning precision through multi-timepoint geometric information.
Solution Approach 2:
The patent extracts only the essential geometric relationship information from multiple frame images needed for positioning, rather than processing all image data. By taking out and isolating the critical geometric parameters (landmark positions, angles, distances) from the full image sequences, the system achieves high positioning precision with reduced processing complexity.
Data Source
AI summary
A processor-implemented method including selecting a first reference landmark from among a first plurality of candidate landmarks related to a parking area of a vehicle in a first frame image corresponding to a first timepoint, determining positioning information of the vehicle by using geometric relationship information of the selected first reference landmark with respect to the vehicle, selecting a second reference landmark from among a second plurality of candidate landmarks in a second frame image corresponding to a second timepoint, the second timepoint being temporally subsequent to the first timepoint, and updating the positioning information using the geometric relationship information of the selected second reference landmark with respect to the vehicle.