Parking Assistance Feature Point Threshold Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parking assistance technologies may still misrecognize objects around a vehicle even when the number of features in a map feature group exceeds a threshold, leading to potential errors during automatic parking.
Innovation Solution
A parking assistance device and method that includes a feature point detector to compare the number of feature points extracted from a camera image during automatic parking with a threshold value greater than the number of feature points learned during a learning travel, and a traveling controller that prevents automatic parking if the number of feature points exceeds this threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of features in map feature group is greater than threshold, then position estimation accuracy is improved, but object misrecognition risk increases
Solution Approach 1:
The patent changes the parameter of feature point number threshold dynamically. During learning travel, a first threshold is used, but during automatic parking, a second threshold greater than the first is applied. This parameter change allows the system to accept more feature points during automatic parking to improve position estimation accuracy while preventing misrecognition by maintaining a higher safety margin through the elevated threshold.
Solution Approach 2:
The patent implements dynamic threshold adjustment based on the operational mode. The feature point number threshold is not fixed but adapts according to whether the vehicle is in learning travel or automatic parking mode. This dynamic approach allows optimal balance between position estimation accuracy and misrecognition prevention for each operational context.
2Measurement precision
If automatic parking is performed with more feature points, then position estimation accuracy is improved, but risk of misrecognition increases
Solution Approach 1:
The patent applies parameter change by setting different feature point number thresholds for different operational phases. During automatic parking, the second threshold is configured to be greater than during learning travel, allowing the system to utilize more feature points for improved position estimation while the elevated threshold acts as a safeguard against misrecognition.
Solution Approach 2:
The system incorporates feedback mechanisms by comparing the actual number of detected feature points against the dynamically adjusted threshold before executing automatic parking. This feedback loop ensures that position estimation accuracy is optimized while misrecognition risk is controlled through continuous monitoring and threshold-based decision making.
3Productivity
If a lower threshold for feature points is used, then automatic parking can be performed more frequently, but position estimation accuracy decreases
Solution Approach 1:
The patent implements dynamic threshold adjustment where the feature point number threshold changes based on operational mode. During learning travel, a lower first threshold allows more parking opportunities, while during automatic parking, a higher second threshold ensures accuracy. This dynamic approach optimizes both productivity and measurement precision across different operational phases.
Solution Approach 2:
The system performs preliminary learning travel to establish baseline feature point data before executing automatic parking. This preliminary action allows the system to accumulate sufficient feature point information during learning phase, enabling more lenient thresholds during learning travel while ensuring accurate position estimation during subsequent automatic parking operations.
Data Source
AI summary
The parking assistance device includes a feature point detector that determines whether a first number of a plurality of feature points extracted from a camera image captured at a start position for automatic parking of a vehicle during the automatic parking is equal to or greater than a third number that is greater than a second number of a plurality of feature points extracted from a camera image captured at the start position during learning travel, and a traveling controller that controls the vehicle not to perform the automatic parking when the first number is equal to or greater than the third number.