Human Tracking Apparatus Multi-Parameter Similarity Normalization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing human tracking methods in moving images suffer from low accuracy due to the use of single parameters and equal weighting of parameters with different meanings, leading to unreliable likelihood calculations and reduced tracking precision.
Innovation Solution
A human tracking apparatus and method that calculates and integrates similarity indices based on multiple parameters such as movement distance, size, orientation, and color distribution, normalizes these indices, and uses them to accurately identify and track individuals across frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single parameter is used for human tracking, then the device complexity is reduced, but the measurement precision of person similarity is low
Solution Approach 1:
The patent segments the person similarity assessment into multiple independent parameters: movement distance, size, orientation, and color distribution. Each parameter is calculated separately and then integrated, allowing comprehensive evaluation without excessive system complexity. This segmentation enables the tracking system to assess person similarity through distinct dimensional analysis.
Solution Approach 2:
The patent transitions from single-parameter tracking to multi-parameter tracking by adding dimensional depth to the similarity assessment. By evaluating movement distance, size, orientation, and color distribution as separate dimensions, the system achieves higher measurement precision while managing complexity through structured multi-dimensional analysis.
2Adaptability or versatility
If multiple parameters with different meanings are equally weighted, then the evaluation comprehensiveness is improved, but the reliability of likelihood calculation is reduced
Solution Approach 1:
The patent applies local quality by assigning different weights to different parameters based on their individual importance and reliability. Rather than uniform weighting, each parameter (movement distance, size, orientation, color distribution) receives a weight tailored to its specific contribution to person similarity, enhancing the overall reliability of the likelihood calculation.
Solution Approach 2:
The patent dynamically adjusts parameter weights based on their statistical properties and reliability metrics. By changing the weight parameters according to each parameter's performance and relevance, the system maintains comprehensive evaluation while ensuring that more reliable parameters have greater influence on the final likelihood calculation.
Data Source
AI summary
A human tracking apparatus and method capable of highly accurately tracking the movement of persons photographed in moving images includes: an image memory 107 that stores an inputted frame image; a human detecting unit 101 that detects persons photographed in the inputted frame image; a candidate registering unit 106 that registers already detected persons as candidates; a similarity index calculating unit 102 that calculates similarity indices indicating the similarity between the persons detected in the inputted frame image and the registered candidates for two or more types of parameters based on the stored frame images in relation to all combinations of the persons and the candidates; a normalizing unit 103 that normalizes the similarity indices; an integrating unit 104 that integrates the normalized indices for each combination of the detected persons and the candidates; and a tracking unit 105 that identifies a person the same as an arbitrary candidate based on the similarity indices.