Ball Game Motion Recognition via Feature Point Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing motion recognition technologies face challenges in accurately distinguishing between sport and non-sport motions, particularly in outdoor sports like golf, where extracting relevant motion parameters and recognizing specific ball game types is difficult due to interference from non-sport activities.

Innovation Solution

A method and apparatus for ball game motion recognition that involves obtaining motion parameters at each sampling time, extracting feature points using predetermined recognition tactics, and recognizing the motion as a specific ball game type based on these features, incorporating a sensor device, motion parameter confirming device, and a processor to filter and process data from tri-axial accelerometers, gyroscopes, and magnetometers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If motion parameters are obtained using sensors during outdoor sports activities, then motion data can be collected for analysis, but it becomes difficult to distinguish between sport motions and non-sport motions (e.g., drinking water, resting, phone calls)

Engineering Contradiction:
Improvemotion recognition accuracyVSAvoidmotion type differentiation
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent segments the continuous motion data into discrete action phases by identifying characteristic feature points (power-assisting path early stage, motion top point, ball hitting time). This segmentation allows the system to distinguish sport motions from non-sport motions by analyzing the sequence and characteristics of these segmented phases, resolving the contradiction between measurement precision and motion type differentiation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the parameter representation from raw continuous motion data to extracted feature points with specific temporal and spatial characteristics. By transforming motion parameters into discrete feature points that represent key phases of ball game motions, the system achieves both precise measurement and effective differentiation between sport and non-sport activities.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If feature points are extracted using multiple recognition tactics, then ball game motion recognition accuracy improves, but system complexity increases

Engineering Contradiction:
Improveball game motion recognition accuracyVSAvoidrecognition system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the complex recognition task into three distinct feature point extraction tactics (power-assisting path early stage, motion top point, ball hitting time). Each tactic focuses on extracting specific characteristic points, making the overall complex recognition process more manageable and implementable while maintaining high accuracy.

Inventive Principle:
Principle #1Segmentation

3Manufacturing precision

If comprehensive motion parameters are collected for detailed analysis, then evaluation quality improves, but data processing time and computational load increase

Engineering Contradiction:
Improvemotion evaluation qualityVSAvoiddata processing time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent extracts only the essential feature points (power-assisting path early stage, motion top point, ball hitting time) from the comprehensive motion parameter data. This extraction approach maintains high evaluation quality by focusing on the most informative characteristics while significantly reducing data processing time and computational requirements compared to analyzing all raw motion parameters.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS8781610B2Method of ball game motion recognition, apparatus for the same, and motion assisting device
Publication Date: 2014.07.15 ZEPP NORTH AMERICA INC
  • US8781610B2 patent drawing
  • US8781610B2 patent drawing
  • US8781610B2 patent drawing

AI summary

The invention provides a method of ball game motion recognition, an apparatus for the same, and a motion assisting device. The method comprises: obtaining motion parameters corresponding to each sampling time for a motion; extracting feature points according to predetermined feature point recognition tactics utilizing the motion parameters obtained, in which the feature point recognition tactics comprise recognition tactics of at least three types of the feature points, comprising: power-assisting path early stage corresponding feature point, motion top point corresponding feature point, and ball hitting time corresponding feature point; and recognizing the motion as a predetermined ball game type if the feature points extracted satisfy feature point requirements of the predetermined ball game type.