Motion Evaluation Apparatus Using Temporal-Spatial Skeletal Deviation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion evaluation systems only assess the similarity of skeletal information at a synchronization time, failing to provide an appropriate evaluation of human motion.
Innovation Solution
A motion evaluation apparatus that extracts skeletal information from images and identifies evaluation target motions by comparing them to registered motion patterns, using an integrated evaluation value that considers deviations in both temporal and spatial axes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only similarity of skeletal information at synchronization time is evaluated, then the evaluation process is simple, but the motion evaluation accuracy is insufficient
Solution Approach 1:
The patent extends the evaluation from a single time point (synchronization moment) to multiple time points (temporal sequence), adding a time dimension to the evaluation. This is achieved by calculating deviation amounts at multiple time points and integrating them to form a comprehensive evaluation value, thereby improving motion evaluation accuracy without excessive complexity increase
Solution Approach 2:
The patent divides the motion evaluation into multiple segments: extracting skeletal information at multiple time points, calculating deviation amounts for each time point, and integrating these deviations. This segmentation allows systematic evaluation of motion sequences while maintaining manageable computational complexity through modular processing
2Measurement precision
If only spatial deviation is considered, then the calculation is straightforward, but the temporal variation of motion cannot be captured
Solution Approach 1:
The patent adds a temporal dimension to the spatial evaluation by calculating deviation amounts at multiple time points and integrating them over time. This creates a two-dimensional evaluation (spatial + temporal) that comprehensively captures motion characteristics while using systematic integration methods to control computational complexity
Data Source
AI summary
A motion evaluation apparatus includes: motion identification unit for extracting skeletal information of a person in an acquired image and identifying an evaluation target motion related to a body of the person based on the extracted skeletal information of the person and a registered motion pattern formed by stored skeletal information; and evaluation unit for evaluating similarity between the evaluation target motion and a sample motion pattern formed by stored skeletal information, based on an integrated evaluation value including a first evaluation value that is based on a deviation amount of the skeletal information in a temporal axis direction and a second evaluation value that is based on a deviation amount of the skeletal information of the person in a spatial axis direction.