Own-Position Estimation Using Position-Adaptive Feature Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing own-position estimating devices face challenges in accurately estimating the position of a moving body in real time, particularly due to uneven feature extraction and distribution, which can lead to decreased accuracy and processing speed.
Innovation Solution
The proposed solution involves an own-position estimating device that includes a determination threshold value adjusting unit. This unit adjusts the determination threshold value for feature extraction based on position information linked to each feature in a database, ensuring suitable feature extraction regardless of the moving body's travel position.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a constant determination threshold value is used for feature extraction, then the processing method is simple, but the number of features or distribution of features becomes uneven according to travel position, decreasing estimation accuracy
Solution Approach 1:
The determination threshold value is changed from a static constant to a dynamic value that varies according to the moving body's position. The threshold value adjusting unit modifies the threshold based on position information from the database, allowing the feature extraction process to adapt to different travel positions and maintain uniform feature distribution throughout the movement area.
Solution Approach 2:
The determination threshold value parameter is modified based on position information. By changing this parameter according to the moving body's location and the pre-stored database of appropriate thresholds for different positions, the system achieves uniform feature extraction across various travel positions while maintaining processing efficiency.
2Measurement precision
If too many features are extracted from the image, then the feature distribution becomes more comprehensive, but the processing speed decreases making real-time estimation difficult
Solution Approach 1:
By dynamically adjusting the determination threshold value parameter based on position information, the system optimizes the balance between feature extraction completeness and processing speed. The threshold is set to extract sufficient features for accurate position estimation while preventing excessive feature extraction that would slow down processing and prevent real-time operation.
3Productivity
If too few features are extracted from the image, then the processing speed is fast, but the accuracy of own-position estimation decreases
Solution Approach 1:
The determination threshold value is adjusted based on position information to ensure sufficient features are extracted for accurate position estimation while maintaining processing speed. The database stores optimized threshold values for different positions that balance feature extraction adequacy with processing efficiency, enabling real-time operation without sacrificing accuracy.
Data Source
AI summary
An own-position estimating device for estimating an own-position of a moving body by matching a feature extracted from an acquired image with a database in which position information and the feature are associated with each other in advance, includes an estimating unit estimating the own-position of the moving body by matching the feature extracted by the extracting unit with the database, and a determination threshold value adjusting unit adjusting a determination threshold value for extracting the feature, in which the determination threshold value adjusting unit acquires the database in a state in which the determination threshold value is adjusted, and adjusts the determination threshold value on the basis of the determination threshold value linked to each of the position information items in the database, and the extracting unit extracts the feature from the image by using the determination threshold value adjusted by the determination threshold value adjusting unit.