Feature Point Filtering Across Image Pyramids for Mobile Position Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing feature point detection methods in position estimation for mobile objects suffer from reduced accuracy due to scale changes, leading to unreliable tracking and estimation, particularly for distant feature points.
Innovation Solution
A feature point processing device generates multiple hierarchy images with varying reduction ratios, detects feature points, and selectively excludes those with pixel accuracy exceeding an allowance value, ensuring only high-accuracy points are used for position estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple hierarchy images are generated to detect feature points for scale invariance, then the accuracy of position estimation is improved, but the processing time increases
Solution Approach 1:
The patent segments the feature point processing into multiple hierarchy levels, where feature points are detected at different reduction ratios and then selectively excluded based on pixel accuracy. This segmentation allows the system to process only the necessary hierarchy levels rather than all levels, reducing overall processing time while maintaining position estimation accuracy.
Solution Approach 2:
The patent applies partial action by selectively excluding feature points from certain hierarchy images based on pixel accuracy thresholds. Instead of processing all feature points from all hierarchy images, the system performs partial processing by excluding low-accuracy points, thereby reducing computation time while preserving the necessary accuracy for position estimation.
2Quantity of substance
If feature points from all hierarchy images are used for position estimation, then more feature points are available for tracking, but the reliability decreases due to low pixel accuracy in distant points
Solution Approach 1:
The patent applies local quality by differentiating the treatment of feature points based on their pixel accuracy. Feature points with high pixel accuracy (from lower reduction ratios) are retained for position estimation, while those with low pixel accuracy (from higher reduction ratios) are excluded. This selective approach ensures that only reliable feature points contribute to the position estimation, maintaining tracking reliability.
Solution Approach 2:
The patent changes the parameter of pixel accuracy as a criterion for selecting or excluding feature points. By introducing pixel accuracy as a filtering parameter based on reduction ratio, the system dynamically determines which feature points to use, thereby maintaining reliability while managing the quantity of feature points used in position estimation.
3Measurement precision
If feature points with low pixel accuracy are excluded, then the position estimation accuracy is improved, but the number of available feature points decreases
Solution Approach 1:
The patent uses pixel accuracy as a dynamic parameter to filter feature points. By setting thresholds based on pixel accuracy derived from reduction ratios, the system selectively excludes low-accuracy points while retaining sufficient high-accuracy points for reliable position estimation. This parameter-based filtering ensures that position estimation accuracy is improved without excessively reducing the number of available feature points.
Data Source
AI summary
Multiple hierarchy images are generated to have sizes that are obtained by reducing a process target image by multiple reduction ratios using the process target image acquired by a camera mounted on a mobile object. A feature point detection process is executed to detect multiple feature points from the hierarchy images. Some of the feature points are selected and excluded as an exclusion feature point such that, among the feature points, one of the feature points having a pixel accuracy exceeding an allowance value is selected as the exclusion feature point. The pixel accuracy is an accuracy per pixel determined according to the reduction ratio of each hierarchy image.