Feature Positioning for Camera Attitude Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing methods for calculating camera positional attitude in mixed reality and augmented reality systems require repeated trial and error in arranging markers, making the setting operation time-consuming due to the fluctuation in precision based on feature arrangement.
Innovation Solution
An information processing apparatus that includes an acquisition unit for features, a setting unit for candidate regions, an evaluation unit to assess these regions, a determination unit to determine feature addition positions, and an output unit to indicate these positions, allowing for precise calculation of camera positional attitude without extensive trial and error.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If markers are arranged through repeated trial and error to improve camera positional attitude calculation precision, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary evaluation of candidate feature addition positions by calculating evaluation values that predict calculation precision improvement. This preliminary assessment allows the user to select optimal positions without repeated trial and error, directly resolving the contradiction by preparing evaluation data in advance.
Solution Approach 2:
The patent introduces an evaluation value as an intermediary metric that mediates between feature arrangement and calculation precision. The evaluation value serves as a predictor that guides feature addition decisions, eliminating the need for direct trial-and-error experimentation while maintaining precision improvement.
2Manufacturing precision
If multiple candidate regions are evaluated to determine optimal feature positions, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The system segments the image into multiple candidate regions and evaluates each independently. This segmentation allows complex evaluation to be broken down into manageable regional assessments, improving feature arrangement precision while keeping the complexity of each evaluation step manageable.
Solution Approach 2:
The patent changes evaluation parameters by calculating different evaluation values for each candidate region based on feature distribution metrics. By varying these parameters systematically, the system achieves precise feature arrangement guidance without requiring overly complex evaluation mechanisms.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In order to shorten the time required for a setting operation of features, an information processing apparatus includes an acquisition unit configured to acquire features used for deriving a positional attitude of an imaging device from an image captured by the imaging device, a setting unit configured to set a plurality of partial regions included in the image as a plurality of candidate regions to which a feature is to be added, an evaluation unit configured to evaluate the plurality of set candidate regions, a determination unit configured to determine a position and/or an orientation of a feature to be newly added based on the plurality of evaluated candidate regions, and an output unit configured to output the determined position and/or the orientation.