Motion Estimation via Distance Map Line Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Algorithms for motion estimation in digital images often fail due to periodic patterns and aperture problems, leading to incorrect pattern matching under physical variations like noise and misalignments.
Innovation Solution
A method that evaluates motion estimation by using a distance map to locate candidate lines passing through local minima points, determining confidence levels, and selecting lines above a threshold, employing techniques like Hough transform and RANSAC algorithm to detect periodic patterns and aperture issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If naïve pattern matching approaches are used for motion estimation, then the algorithm is simple and fast, but it fails to correctly match patterns under periodic patterns and aperture problems
Solution Approach 1:
The patent segments the pattern matching process into multiple stages: initial distance map computation, line detection through Hough transform, aperture problem detection, and periodic pattern detection. This segmentation allows the system to handle complex cases by breaking them into manageable detection stages, improving reliability without overwhelming computational complexity.
Solution Approach 2:
The patent performs preliminary detection of aperture problems and periodic patterns before final pattern matching. By computing the distance map first and detecting structural issues (aperture problems, periodic patterns) in advance, the system can adjust its matching strategy accordingly, preventing failed matches before they occur.
2Measurement precision
If distance map computation is performed for all blocks in search area, then motion estimation coverage is complete, but computational time increases
Solution Approach 1:
The patent extracts and processes only the distance map data that is essential for motion estimation, rather than processing all raw image data. By working with the computed distance map and its derived features (local minima, line structures), the system achieves accurate motion estimation with reduced computational overhead compared to processing full image blocks.
Solution Approach 2:
The patent computes distance maps for the entire search area to ensure complete coverage, but then uses selective processing techniques (line detection, aperture problem detection) to identify and focus on only the critical regions that require detailed analysis, effectively balancing completeness with efficiency.
Data Source
AI summary
A method of evaluating motion estimation between a pair of digitized images includes receiving a distance map between a source block in a source image and all the blocks in a search area in a target image, scanning each column of the distance map, and saving indices of a minimum distance value for each column, scanning each row of the distance map, and saving indices of a minimum distance value for each row, locating candidate lines that pass through at least some local minima points that correspond to locations in the distance map of the minimum distance value in each of the columns or the minimum distance value in each of the rows determining a confidence level for each candidate line that passes through at least some of the local minima points, and selecting those candidate lines whose confidence level is greater than a predetermined threshold value.