Angular Position Tracking via Multi-Feature Image Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional motion estimation techniques struggle with accurately tracking the rotary position of electric machines from video images, leading to significant measurement deviations due to slight inaccuracies, especially when direct measurement with a position transducer is inhibited by packaging constraints or other factors.
Innovation Solution
A method involving a processing system that accesses images of a system under analysis, determines angular position estimates based on edges of features such as a multi-colored disk and impeller blades, and uses edge detection and transformation techniques to identify lines and angles, correlating these to determine a final angular position estimate with enhanced position resolution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional motion estimation techniques are used to track rotary position from video images, then the system is simple and does not require direct transducer mounting, but measurement accuracy deteriorates due to slight inaccuracies resulting in large deviations
Solution Approach 1:
The patent segments the image processing into distinct stages: edge detection to identify feature boundaries, feature identification to locate specific components (multi-colored disk, impeller blades), and angular position calculation. This segmentation allows each stage to be optimized independently, improving measurement precision while managing complexity through structured processing pipelines.
Solution Approach 2:
The patent introduces intermediate processing steps including edge detection algorithms and feature extraction routines that act as mediators between the raw video image and the final angular position estimate. These intermediaries transform the image data through multiple processing layers, enhancing measurement accuracy by systematically reducing errors at each transformation stage.
2Measurement precision
If multiple features are tracked to enhance position resolution, then measurement accuracy improves, but processing time and computational load increase
Solution Approach 1:
The patent performs preliminary edge detection and feature identification before angular position calculation. By pre-identifying features of interest (multi-colored disk edges, impeller blade edges) and their expected angular relationships, the system reduces computational load during the main tracking phase, allowing multiple features to be processed efficiently without excessive time loss.
Solution Approach 2:
The patent processes multiple features (edges of multi-colored disk, edges of impeller blades) beyond what a single feature would provide. This excessive action of tracking more features than minimally required enhances position resolution through redundancy and cross-validation, while the system manages the associated computational load through efficient processing algorithms.
3Reliability
If edge detection and transformation techniques are applied to isolate features, then feature identification accuracy improves, but computational complexity increases
Solution Approach 1:
The patent replaces direct mechanical measurement (transducer mounting) with optical field-based image processing. Edge detection algorithms and mathematical transformations substitute for physical contact measurement, achieving reliable feature identification through field analysis rather than mechanical interaction, thereby improving reliability while avoiding the complexity of direct transducer integration.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A processing system is configured to access an image of a system under analysis including a plurality of features of interest. The processing system determines a first angular position estimate of a first feature of interest (206) in the image and determines a second angular position estimate of a second feature of interest (214) in the image (200). The processing system determines a final angular position estimate for the system under analysis based on a relationship between the first angular position estimate and the second angular position estimate. The final angular position estimate is output.