Motion Recognition Device for Gymnastics Skill Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gymnastics performance evaluation techniques, such as those using 3D laser sensors, are inefficient due to the need for numerous prototypes to distinguish various skills, leading to time-consuming recognition processes.
Innovation Solution
A system utilizing a 3D sensor and skeleton recognition device to generate three-dimensional data, which is then processed by a motion recognition device to evaluate gymnastic skills and difficulty levels based on feature points, body vectors, and predefined rules, allowing for efficient segmentation and scoring of movements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple prototypes are prepared for each skill to distinguish various types of skills, then the accuracy of skill identification is improved, but the time required for recognition increases
Solution Approach 1:
The skill recognition process is segmented into multiple stages: first dividing the movement into phases based on key frame detection, then identifying skills within each phase using phase-specific prototypes, and finally combining results to determine the complete skill sequence. This segmentation allows the system to use fewer prototypes at each stage while maintaining overall recognition accuracy.
Solution Approach 2:
The system performs preliminary actions by detecting key frames and dividing movements into phases before conducting detailed skill identification. This preliminary structuring of the data allows subsequent skill recognition to be more efficient and accurate, reducing the time needed for comprehensive skill identification.
2Measurement precision
If comprehensive skill evaluation is performed to accurately assess gymnastic performance, then the evaluation accuracy is improved, but the processing complexity increases
Solution Approach 1:
The evaluation process is segmented into distinct components: key frame detection, phase division, skill identification for each phase, and difficulty level determination. Each component handles a specific aspect of the evaluation, reducing the complexity of any single processing step while maintaining comprehensive evaluation accuracy.
Solution Approach 2:
The system dynamically adjusts the evaluation process based on the detected movement characteristics. Different phases of the movement are evaluated using phase-appropriate criteria and prototypes, allowing the system to adapt its processing complexity to the specific skill being evaluated rather than applying a uniform complex evaluation to all movements.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A motion recognition device (100) includes a segmentation unit (153), an identification unit (154), and a first evaluation unit (155). In the segmentation unit (153), a plurality of frames including positional information on feature points that correspond to a predetermined part or a joint part of the body of a subject are segmented based on a position of the predetermined part of the body of the subject in time series, and accordingly the plurality of frames are classified into a plurality of groups in time series. For each group, the identification unit (154) identifies a type of a basic motion that corresponds to the group based on movement of the feature points included in consecutive frames. The first evaluation unit (155) evaluates a skill and a difficulty level of the motion performed by the subject based on the order of each type of the basic motion that corresponds to the group that is consecutive in time series.