AVPS Marker Calibration for Autonomous Parking Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AVPS systems face challenges in maintaining accurate localization of autonomous vehicles due to changes in camera mounting angles or positions, leading to decreased localization accuracy.
Innovation Solution
A calibration method is introduced that recognizes coded markers in a parking facility, estimates their position and orientation, calculates errors compared to a marker database, and performs calibration when errors exceed a preset threshold to ensure accurate vehicle localization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If camera mounting angle or position changes due to collision or other reasons, then the system continues to operate, but localization accuracy decreases
Solution Approach 1:
The system performs preliminary calibration by capturing images of coded markers at known positions before normal operation. This establishes reference data that compensates for camera mounting deviations, allowing the system to maintain localization accuracy even when camera position changes due to collisions or other factors.
Solution Approach 2:
The system continuously captures images of coded markers during operation and compares their detected positions with expected positions from the high-definition map. This feedback mechanism identifies deviations caused by camera position changes and triggers recalibration when necessary, maintaining ongoing localization accuracy.
2Measurement precision
If calibration is performed frequently to maintain accuracy, then localization precision improves, but system complexity and operation time increase
Solution Approach 1:
The system performs self-calibration by automatically capturing images of coded markers, detecting their positions, calculating deviations from expected positions, and adjusting calibration parameters without requiring external intervention. This reduces operational complexity while maintaining precision.
Solution Approach 2:
The system changes calibration parameters based on detected deviations from coded marker positions. By adjusting these parameters dynamically, the system maintains localization precision without requiring complete recalibration procedures, reducing operational complexity.
3Measurement precision
If calibration is performed frequently to maintain accuracy, then localization precision improves, but processing time increases
Solution Approach 1:
The system performs partial calibration by only processing images of coded markers that are detected and relevant to current localization needs. This selective approach maintains precision while reducing the time required compared to complete calibration procedures.
Solution Approach 2:
The system skips calibration steps when deviations are within acceptable thresholds by comparing detected marker positions with expected positions. Only when deviations exceed thresholds does the system perform full calibration, reducing average processing time while maintaining precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An apparatus and a method for improving the localization accuracy of an autonomous vehicle using an AVPS marker. An example method comprises recognizing a first coded marker around an entry space in a parking facility to generate coded marker recognition information, estimating a position and orientation of the recognized coded marker based on the coded marker recognition information and parameters of at least one camera, obtaining information on a second coded marker with the same ID as the recognized coded marker from a marker database containing information on an ID, position, orientation and size of each of a plurality of coded markers installed in the parking facility, calculating an error based on the coded marker recognition information and the information on the second coded marker, and performing calibration based on the error when the error is greater than or equal to a preset threshold.