3D Skeleton Motion Recognition for Accurate Sports Element Scoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional technologies fail to accurately evaluate athletic performances by distinguishing between stationary and moving motions, which are crucial for determining the type and difficulty of elements in sports, leading to inconsistent scoring.

Innovation Solution

An element recognition system using a 3D laser sensor and an element recognition apparatus that analyzes skeletal information from distance images to differentiate between stationary and moving motions, employing threshold-based segmentation and success conditions to identify elements accurately.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional technology uses two-dimensional silhouette images to detect key poses and recognize elements, then the evaluation process is simple, but the measurement precision of motion types is insufficient to distinguish stationary and moving motions

Engineering Contradiction:
Improvemotion type recognition accuracyVSAvoidevaluation system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the evaluation process into distinct phases: detecting key poses, determining motion types (stationary vs. moving), and recognizing elements based on motion combinations. This segmentation allows each phase to be handled with appropriate precision without overwhelming system complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from two-dimensional silhouette image analysis to three-dimensional spatial coordinate analysis. By using 3D coordinates to represent key pose positions and calculating spatial relationships, the system achieves higher measurement precision for distinguishing motion types while maintaining manageable complexity through structured 3D data processing.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If the system recognizes elements based only on key pose combinations without considering motion types, then the recognition process is fast, but the reliability of element evaluation is insufficient

Engineering Contradiction:
Improveelement evaluation accuracyVSAvoidrecognition processing speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent performs preliminary classification of motion types (stationary vs. moving) before final element recognition. By determining motion characteristics in advance, the system establishes a reliable foundation for element evaluation, ensuring that subsequent recognition processes can proceed efficiently with already-filtered information.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces motion type determination as an intermediary step between key pose detection and element recognition. This intermediary process acts as a bridge that processes raw pose data into meaningful motion classifications, which then guide the final element recognition, improving both reliability and processing efficiency.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Manufacturing precision

If the system evaluates athletic performance without distinguishing stationary and moving motions, then the evaluation process is simple, but the manufacturing precision of element classification is insufficient

Engineering Contradiction:
Improveelement classification accuracyVSAvoidmotion analysis system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent applies different evaluation criteria and analysis methods to different motion types. Stationary motions are evaluated with specific positional accuracy requirements, while moving motions are evaluated with velocity and trajectory considerations. This local quality approach ensures high classification precision for each motion type without requiring a single overly complex system.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3726468B1Technique recognition program, technique recognition method, and technique recognition system
Publication Date: 2025.07.16 FUJITSU LTD
  • EP3726468B1 patent drawingFigure 1~2
  • EP3726468B1 patent drawingFigure 3~4
  • EP3726468B1 patent drawingFigure 5~6

AI summary

An element recognition apparatus (100) segments three-dimensional skeleton information including a subject performing a series of performances, acquired in chronological order, into a plurality of units in accordance with a predetermined rule. The element recognition apparatus (100) determines whether a postural motion corresponding to a first unit among the units is a first motion having a feature indicating that the subject is stationary or a second motion different from the first motion. The element recognition apparatus (100) determines, based on a determination result corresponding to the first unit and a recognition result of recognition on the type of moving motion in a second unit that is continuous with the first unit, an element corresponding to the combination including at least the first unit and the second unit.