一种运动损伤严重程度评估方法及评估装置
By extracting joint coordinates and joint features using the VIBE model, and combining high-frequency functions and a lightweight three-feature three-scale motion network, the accuracy and complexity issues of Parkinson's disease movement injury assessment in existing technologies are resolved, achieving higher assessment accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHONGQING UNIV OF POSTS & TELECOMM
- Filing Date
- 2023-06-29
- Publication Date
- 2026-07-17
AI Technical Summary
Existing computer vision technologies suffer from low accuracy, high network model complexity, incomplete generalization of input features, and insufficient feature extraction in assessing the degree of motor impairment in Parkinson's disease.
The VIBE model is used to extract joint coordinates, calculate joint collection distance features and normalized Cartesian coordinates, combine high-frequency functions for position encoding, and perform feature processing through cascaded one-dimensional convolutions and fully connected layers. A lightweight three-feature three-scale motion network model is used for evaluation.
It improves the accuracy and efficiency of assessing the degree of motor impairment in Parkinson's disease, reduces the complexity of the network model, and achieves higher accuracy.
Smart Images
Figure CN116798639B_ABST