Own-Position Estimation With Adaptive Feature Threshold Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing own-position estimating devices face challenges in achieving real-time accuracy due to uneven feature extraction and distribution, leading to decreased processing speed and estimation accuracy, particularly in environments with few or excessive features.
Innovation Solution
The device adjusts determination threshold values, such as light-dark and corner thresholds, to balance feature extraction based on the travel position, ensuring even feature distribution and preventing accuracy and speed degradation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a constant determination threshold value is used when extracting features from images, then the extraction process is simple and fast, but the number and distribution of extracted features become uneven according to travel position, decreasing estimation accuracy
Solution Approach 1:
The patent applies dynamics by making the determination threshold value adjustable rather than fixed. The threshold is dynamically changed based on the travel position of the moving body, allowing the system to adapt to different environmental conditions (such as varying feature densities in different locations) while maintaining both processing efficiency and estimation accuracy.
Solution Approach 2:
The patent changes the parameter of the determination threshold value based on travel position. By adjusting this parameter according to the specific location and environmental conditions, the system optimizes feature extraction to ensure sufficient features are extracted without overwhelming processing requirements, thus balancing speed and accuracy.
2Measurement precision
If the determination threshold value is adjusted to increase the number of extracted features, then estimation accuracy improves, but processing speed decreases making real-time estimation difficult
Solution Approach 1:
The patent applies local quality by adjusting the determination threshold value according to the specific travel position and local environmental conditions. Rather than using a uniformly high threshold that would slow processing everywhere, the system locally adapts the threshold to match the feature density and characteristics of each specific location, optimizing the balance between feature count and processing speed for each area.
Solution Approach 2:
The system changes the determination threshold parameter dynamically based on travel position information. This allows the patent to extract an appropriate number of features for accurate estimation without consistently using a low threshold that would slow processing, thus maintaining real-time performance while improving accuracy where needed.
Data Source
Figure 1
Figure 2
Figure 3
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 image acquiring unit acquiring the image, an extracting unit extracting the feature from the image acquired by the image acquiring unit, 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.