Skeleton Motion Segmentation for Accurate Gymnastics Element Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for evaluating gymnastics performance using 3D sensors struggle with accurate determination of elements due to reliance on feature amount conditions, leading to deteriorated determination accuracy.

Innovation Solution

A method involving a processor to detect segment points, integrate them, and adjust them to satisfy predetermined basic motion conditions using a trained skeleton inference model to enhance accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If segment points are detected based on feature amount conditions, then basic motions can be identified, but determination accuracy of gymnastics elements deteriorates

Engineering Contradiction:

Improvebasic motion identificationVSAvoidelement determination accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the gymnastics performance into multiple basic motions by detecting segment points. Each basic motion is defined by a sequence of skeleton frames between segment points, allowing systematic analysis of complex elements while maintaining identification efficiency

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transitions from two-dimensional feature amount comparison to three-dimensional spatial analysis by incorporating skeleton frame coordinates and body part positions. This dimensional enhancement enables more accurate element determination while preserving basic motion identification capabilities

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Device complexity

If feature amount conditions are used for element determination, then processing is simplified, but determination accuracy deteriorates

Engineering Contradiction:

Improvedetermination process complexityVSAvoidelement determination accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces traditional mechanical feature amount comparison with an information-based skeleton frame analysis system. By using coordinate data and spatial relationships from skeleton frames, the system achieves higher accuracy without significantly increasing operational complexity

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the determination parameters from simple feature amounts to comprehensive skeleton frame attributes including body part positions, joint angles, and spatial coordinates. This parameter transformation enables more precise element identification while maintaining processing efficiency

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260038305A1Determination method, non-transitory computer-readable recording medium, and information processing apparatus

Publication Date: 2026.02.05 FUJITSU LTD

AI summary

A determination method includes detecting a plurality of segment points based on a plurality of frames including a first feature amount indicating a feature amount related to a joint of a subject, integrating two or more segment points among the plurality of segment points, and adjusting a segment point to be integrated so that a second feature amount specified from the first feature amounts of a plurality of frames included in an integrated section of the segment points satisfies a condition of a feature amount of a predetermined basic motion, by using a processor.