Multi-Camera AVPS Marker Localization for Distortion-Aware Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting and recognizing coded markers in automated valet parking systems (AVPS) suffer from low accuracy due to distance and distortion issues, making it difficult to accurately estimate the distance to the marker and measure the vehicle's position.
Innovation Solution
A method and apparatus that utilize multiple cameras to recognize corner points of coded markers, calculate their coordinates, and estimate the marker's position, width, and angle, while filtering and weighting the markers to account for distortions and distances, ultimately converting the marker data into a unified coordinate system for precise vehicle localization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single camera is used to detect coded markers, then the device complexity is low, but the measurement precision of marker position and distance is insufficient
Solution Approach 1:
The patent combines multiple cameras to form a camera array system for detecting coded markers. By merging the detection capabilities of multiple cameras, the system achieves higher measurement precision in determining marker position, width, and angle while maintaining manageable device complexity through coordinated processing of camera data.
Solution Approach 2:
The patent transitions from single-camera two-dimensional detection to multi-camera three-dimensional detection. By adding spatial dimensions through multiple camera viewpoints, the system can accurately estimate distance to markers and detect their spatial orientation, significantly improving measurement precision without excessive complexity increase.
2Measurement precision
If the camera is positioned far from the marker, then the field of view is wide, but the measurement precision of marker coordinates decreases
Solution Approach 1:
The patent merges data from multiple cameras positioned at different locations to achieve both wide field of view and high measurement precision. Each camera captures marker information from its viewpoint, and the combined data provides accurate coordinate measurement while covering a larger area than any single camera could achieve alone.
3Reliability
If conventional marker detection methods are used, then the detection process is simple, but the reliability of vehicle localization is low
Solution Approach 1:
The patent performs preliminary filtering and validation of detected markers before using them for vehicle localization. By pre-processing marker data to verify detection quality and filter out unreliable markers, the system enhances localization reliability while managing processing complexity through structured validation protocols.
Solution Approach 2:
The patent implements feedback mechanisms where detected marker information is continuously validated and used to correct vehicle position estimates. The system uses marker detection results to refine localization accuracy, creating a closed-loop process that improves reliability while the structured feedback mechanism keeps processing complexity manageable.
Data Source
AI summary
The present disclosure provides a method and an apparatus for vehicle localization using AVPS marker.According to at least one embodiment, the present disclosure provides a method for performing localization by a vehicle including a plurality of cameras, including recognizing corner points of a coded marker from an image acquired from each of the cameras, calculating a position, a width, and an angle of the coded marker by using the coordinates of the corner points, filtering the coded marker, calculating a final weight of the coded marker, generating a position and an angle of a local coded marker, rotationally transforming the position of the local coded marker by using information on markers in a parking facility and the angle of the local coded marker, and measuring the position of the vehicle by using the position of the local coded marker and the final weight.