Motion Recognition via Dynamic Programming Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion recognition technologies face challenges in accurately and automatically scoring complex human motions in athletic competitions, such as gymnastics, due to the complexity and variability of human motion patterns, which limits the effectiveness of human judgment and requires advanced sensing and processing technologies.
Innovation Solution
A motion recognition system that segments human motion into basic motions using dynamic programming, classifies each segment, and converts the motion into a sequence of high rank symbols to evaluate and score techniques, enabling automatic interpretation and scoring by treating motion recognition as an optimization problem.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If motion recognition is performed by segmenting and classifying basic motions, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The motion recognition system segments complex human motions into discrete basic motion units (BMUs) through temporal segmentation. Each BMU represents a fundamental motion primitive that can be independently classified and recombined. This segmentation approach enables precise recognition of complex motions by breaking them down into manageable components, directly improving measurement precision while providing a structured framework for classification.
Solution Approach 2:
The system transforms continuous motion data into discrete symbolic representations by changing the parameter space. Motion segments are classified into discrete BMU categories, and sequences of BMUs are represented as symbolic strings. This parameter transformation from continuous to discrete domain simplifies the recognition process and enables the use of efficient sequence matching algorithms, addressing the complexity issue.
2Productivity
If automatic scoring technology is implemented, then productivity is improved, but reliability decreases
Solution Approach 1:
The system performs preliminary classification of motion segments into basic motion units before final technique identification and scoring. This preliminary action creates a structured intermediate representation that facilitates more reliable automated scoring by establishing a consistent framework for evaluating motion sequences. The pre-classification of BMUs ensures that subsequent scoring operations work with standardized, well-defined motion primitives.
Solution Approach 2:
The system incorporates evaluation functions that assess the quality and correctness of identified techniques by analyzing the sequence of basic motion units. The feedback mechanism compares the recognized BMU sequences against known technique patterns, providing verification and correction capabilities that enhance reliability. This feedback loop ensures that automated scoring maintains high accuracy by continuously validating results against established criteria.
Data Source
AI summary
The invention relates to automatic discovery and evaluation of a motion by treating motion recognition as an optimization problem by considering a series of basic motions obtained by segmenting a subject motion. The method comprises segmenting time series data defining a motion of a subject into a plurality of segments, classifying each segment into a class for a basic motion by using time series data of the segment, and converting the motion of the subject to a sequence of high rank symbols in which each high rank symbol is formed from a series of the basic motions, wherein a function that calculates a score based on a set of a high rank symbol and a sequence of basic motions is provided and the motion of the subject is converted to the sequence of the high rank symbols by an optimization calculation using dynamic programming.