Height Estimation Using Correction Coefficients for Missing Feature Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating the height of a subject from an image are inaccurate when not all feature points along the subject's skeleton are extracted, especially when features are obscured by objects or obstacles.
Innovation Solution
A height estimation method that involves extracting feature point coordinates from input images, estimating subject and object frame coordinates, generating a distance addition pattern and correction coefficients for missing feature points, and using these patterns to accurately estimate the subject's height even when some feature points are not extracted.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all feature points are extracted to improve height estimation accuracy, then measurement precision improves, but reliability deteriorates when feature points are obscured or not captured
Solution Approach 1:
The patent applies partial action by estimating height using only the subset of feature points that are successfully extracted, rather than requiring all feature points. The system calculates height based on available feature points (e.g., head to waist, waist to knee) and uses correction coefficients to compensate for missing segments, enabling reliable estimation even when some feature points are obscured or not captured in the image
Solution Approach 2:
The patent changes the parameter representation by introducing correction coefficients that adjust the contribution of different feature point distances based on which points are missing. Instead of requiring fixed all feature points, the system dynamically modifies the estimation parameters (correction coefficients) according to the actual extracted feature points, maintaining accuracy despite varying observation conditions
2Productivity
If feature points are extracted from images with obscured subjects, then productivity improves by processing more images, but measurement precision deteriorates due to missing feature points
Solution Approach 1:
The patent enables processing of images with partially obscured subjects by using only the visible feature points. Instead of discarding images where not all feature points are visible (which would maintain high accuracy but reduce throughput), the system processes these images with partial feature point sets and applies correction coefficients to maintain acceptable estimation accuracy, thereby improving overall productivity
Solution Approach 2:
The patent uses a lightweight correction coefficient mechanism that can be quickly applied to each image independently. Rather than employing complex, time-consuming methods to recover missing feature points or reject problematic images, the system applies simple computational corrections that are fast to compute, enabling high-throughput processing with minimal loss in accuracy
Data Source
AI summary
A height estimation method performed by a height estimation apparatus includes a first feature point extraction step of extracting a feature point coordinate, a first coordinate estimation step of estimating a coordinate of a first subject frame, a pre-generation step of deriving a height of the first subject frame and generating a distance addition pattern and a correction coefficient for an individual missing pattern, a second feature point extraction step of extracting a feature point coordinate from a second input image, a second coordinate estimation step of estimating a coordinate of a second subject frame and estimating a coordinate of an object frame, a subject data selection step of selecting the individual missing pattern and the correction coefficient in accordance with the feature point coordinate, an object data selection step of selecting an object height, and a height estimation step of adding up a distance between a feature point coordinate and another feature point coordinate extracted in accordance with the missing pattern and deriving an estimated value of a height of the subject in accordance with a result of adding up the distance, the correction coefficient, the object height, and the coordinates of the object frame.