3D Measurement Edge Weighting for Position Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for measuring the position and orientation of objects in mixed reality and robotic tasks face challenges due to unstable edge detection, high processing loads, and insufficient or biased edge observability, leading to precision drops when view-points change.
Innovation Solution
A three-dimensional measurement apparatus that generates view-point images, detects edges, calculates reliabilities, and weights edges based on these reliabilities to improve the precision of position and orientation calculations, using a reliability-assigned model to associate edges from captured images with a three-dimensional geometric model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If edges are detected from an entire two-dimensional image to ensure comprehensive edge observability, then the position and orientation measurement precision is improved, but the processing load increases significantly
Solution Approach 1:
The patent segments the edge detection process by dividing the two-dimensional image into multiple regions and detecting edges in each region separately. This allows comprehensive edge observability while reducing the processing load compared to detecting all edges from the entire image at once. The segmentation enables parallel processing and focuses computational resources on relevant areas.
Solution Approach 2:
The patent applies local quality by assigning different weights to different edges based on their reliability and observability characteristics. Edges with higher reliability and better observability across multiple view-points are given higher weights in the position and orientation calculation. This selective weighting improves measurement precision without requiring all edges to be processed equally, thus reducing overall processing load.
2Measurement precision
If edges are detected from the entire two-dimensional image to improve edge observability, then the position and orientation measurement precision is improved, but the processing load increases
Solution Approach 1:
The patent segments the edge detection process by dividing the two-dimensional image into multiple regions and detecting edges in each region separately. This allows comprehensive edge observability while reducing the processing load compared to detecting all edges from the entire image at once. The segmentation enables parallel processing and focuses computational resources on relevant areas.
Solution Approach 2:
The patent applies local quality by assigning different weights to different edges based on their reliability and observability characteristics. Edges with higher reliability and better observability across multiple view-points are given higher weights in the position and orientation calculation. This selective weighting improves measurement precision without requiring all edges to be processed equally, thus reducing overall processing complexity.
3Measurement precision
If all edges are used in position/orientation calculation to maximize edge utilization, then the measurement precision is improved, but errors from background edges and unreliable edges increase
Solution Approach 1:
The patent applies local quality by assigning different weights to different edges based on their reliability and observability characteristics. Edges with higher reliability and better observability across multiple view-points are given higher weights in the position and orientation calculation. This selective weighting improves measurement precision while filtering out errors from background edges and unreliable edges, as they receive lower or zero weights.
Solution Approach 2:
The patent performs preliminary evaluation of edge reliability and observability before the position and orientation calculation. By pre-calculating weights for each edge based on their characteristics and performance across multiple view-points, the system prepares a filtered and weighted set of edges that are more likely to be accurate. This preliminary action prevents unreliable edges from degrading the measurement precision.
4Productivity
If a simple geometric model is used to reduce model complexity, then the processing load is reduced, but the ability to accurately represent the measurement object decreases
Solution Approach 1:
The patent applies local quality by assigning different weights to different edges based on their reliability and observability characteristics. Edges with higher reliability and better observability across multiple view-points are given higher weights in the position and orientation calculation. This selective weighting improves measurement precision without requiring all edges to be processed equally, thus reducing overall processing load.
Data Source
AI summary
A three-dimensional measurement apparatus generates a plurality of view-point images obtained by observing a measurement object from a plurality of different view-points using a three-dimensional geometric model, detects edges of the measurement object from the plurality of view-point images as second edges, calculates respective reliabilities of first edges of the three-dimensional geometric model based on a result obtained when the second edges are associated with the first edges, weights each of the first edges based on the respective reliabilities, associates third edges detected from a captured image with the weighted first edges, and calculates a position and an orientation of the measurement object based on the association result.