Motion-aware and dual-stream spatio-temporal graph convolution based action quality assessment method

By using a method based on motion perception and dual-stream spatiotemporal graph convolution, the position and orientation features of rehabilitation movements are extracted, dynamically grouped, and self-attention mechanism is utilized. This solves the problem of inflexible joint synergy modeling in existing technologies and achieves high-precision rehabilitation movement quality assessment.

CN121811503BActive Publication Date: 2026-06-23CHANGCHUN UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202512046231.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-12-31
Publication Date
2026-06-23
Estimated Expiration
2045-12-31

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately model inter-joint synergy in rehabilitation movement quality assessment. Fixed joint grouping strategies lack flexibility, while fully adaptive grouping lacks prior knowledge constraints, resulting in insufficient reliability of assessment results.

Method used

We employ a method based on motion perception and dual-stream spatiotemporal graph convolution. By acquiring rehabilitation action skeleton sequence data, we extract position and orientation data streams, extract spatiotemporal features using dual-stream STGCN branches, design a motion perception dynamic grouping module to generate grouping masks, and model the feature correlation between groups and their ins and outs through a multi-head self-attention mechanism. Finally, we construct a regression head for evaluation.

Benefits of technology

It significantly improves the model's evaluation accuracy and robustness, can distinguish subtle differences in the quality of action completion, reduces the mean absolute error by about 26.5%, achieves state-of-the-art evaluation results on public datasets, and has good robustness and adaptability.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The motion quality evaluation method based on motion perception and double-flow space-time graph convolution relates to the motion quality evaluation field, solves the problems that the existing rehabilitation motion quality evaluation method is difficult to accurately model the cooperation between joints, the fixed joint grouping strategy is not flexible enough, the model has insufficient recognition of the detail differences of complex rehabilitation motions, and the reliability of the evaluation result is affected, a dynamic joint grouping strategy based on motion amplitude driving is provided, a double-flow STGCN architecture is designed, the position and orientation information of the joints are processed respectively and then fused, a two-stage self-attention module SADG is developed, the inter-group time sequence mode and the intra-group spatial relationship are modeled in stages, and multi-granularity feature interaction fusion is realized. The attention mechanism introduces a constraint guided by the motion amplitude, so that the attention weight is more interpretable and has physical meaning.
Need to check novelty before this filing date? Find Prior Art