Feature Point Reliability Evaluation for Vibration Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing free viewpoint video generation systems face errors in vibration correction due to unstable feature points, which are difficult to exclude even with statistical processing, leading to erroneous corrections and requiring significant user effort to verify feature points across multiple image capturing apparatus.
Innovation Solution
An image processing apparatus that acquires and selects feature points based on edge intensities, evaluates their reliability, and presents this information to users, allowing for the exclusion of unstable features and ensuring accurate vibration correction by aligning images from different viewpoints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If feature portions are selected from captured images for vibration correction, then vibration correction can be performed, but erroneous correction occurs due to unstable feature portions
Solution Approach 1:
The patent changes the selection criterion for feature portions from arbitrary or manual selection to automatic selection based on edge intensity values. By using edge intensity as a parameter to identify stable feature portions, the system automatically filters out unstable features that would cause erroneous vibration correction, thus improving both reliability and measurement precision simultaneously
2Productivity
If all detected feature portions are used for vibration correction, then correction can be performed quickly, but correction accuracy decreases due to unstable features
Solution Approach 1:
The system performs self-evaluation of feature portion stability by automatically calculating edge intensity values and using these values to select appropriate feature portions. This self-service mechanism eliminates the need for manual verification of each feature portion while ensuring that only stable features are used, thereby maintaining high productivity without sacrificing reliability
3Measurement precision
If manual verification of feature portions is performed, then correction accuracy improves, but time and effort required increases significantly
Solution Approach 1:
The patent replaces the mechanical process of manual feature portion verification with an automated computational system that calculates edge intensity values and selects feature portions based on predetermined thresholds. This substitution maintains high measurement precision by objectively evaluating feature stability while eliminating the time and effort loss associated with manual verification of numerous feature portions across multiple image capturing apparatus
Data Source
AI summary
To improve user convenience as to adjustment for vibration correction of a captured image captured by an image capturing apparatus, a feature portion evaluation unit refers to feature portions selected by a feature portion selection unit and determines whether feature portions necessary for vibration isolation have been acquired from a reference image. The feature portion evaluation unit has the function of notifying information about the feature portions of the reference image in a case where the acquired feature portions do not satisfy a predetermined condition, that is, in a case where the reliability of the acquired feature portions does not reach a predetermined level.