Subject Tracking Device Normalizing Similarity Factors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object tracking devices fail to ensure high accuracy in similarity level calculations for images with varying gains applied to different components like brightness and chrominance, leading to incorrect subject positioning.
Innovation Solution
A subject tracking device that normalizes similarity factors for brightness and chrominance components using pre-calculated normalizing values, and optionally weights these factors based on image characteristics, ensuring uniform evaluation across components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If similarity factors are calculated for each image component (brightness and chrominance) separately, then the calculation can account for component-specific characteristics, but the accuracy deteriorates when different gains are applied to various components
Solution Approach 1:
The patent applies preliminary action by pre-calculating normalizing values for each image component (brightness and chrominance) based on their respective gains. These normalizing values are stored and then applied during similarity calculation to compensate for gain differences. This preliminary preparation ensures that when similarity factors are calculated for each component separately, the resulting values are normalized and can be accurately combined, thus resolving the accuracy deterioration caused by different component gains.
2Measurement precision
If multiple characteristics components are processed independently, then component-specific similarity can be calculated, but the overall similarity calculation becomes complex and less reliable
Solution Approach 1:
The patent applies parameter changes by introducing normalizing values that transform the similarity factors of different image components into a unified scale. Each component's similarity factor is multiplied by its corresponding normalizing value, which adjusts for gain differences. This parameter transformation simplifies the overall calculation by enabling straightforward addition of normalized component similarities, thereby reducing complexity while maintaining high measurement precision for component-specific similarities.
Data Source
AI summary
A subject tracking device includes: a first similarity factor calculation unit that compares an input image assuming characteristics quantities corresponding to a plurality of characteristics components, with a template image assuming characteristics quantities corresponding to the plurality of characteristics components, and calculates a similarity factor indicating a level of similarity between the input image and the template image in correspondence to each of the plurality of characteristics components; a normalization unit that normalizes similarity factors corresponding to the plurality of characteristics components having been calculated by the first similarity factor calculation unit; and a second similarity factor calculation unit that calculates a similarity factor indicating a level of similarity between the input image and the template image based upon results of normalization achieved via the normalization unit.