Spinal degenerative disease intelligent rehabilitation auxiliary training system based on deep learning
A degenerative disease and deep learning technology, applied in the field of video sequence recognition and evaluation system based on deep learning, can solve problems such as low time complexity and failure to meet real-time processing performance requirements, and achieve a balance between accuracy and speed performance, high The effect of applying value
Pending Publication Date: 2022-02-25
FUDAN UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In computer vision tasks, video behavior recognition is a very challenging field. The method based on RGB frame input often cannot meet the performance requirements of real-time processing. The method based on skeleton sequence has lower time complexity, but in the reasoning process Will rely on the extraction of skeleton information
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0066] In the present invention, the real-time classification model structure (layered body attention LSTM network) of TCM Daoyin action is as follows: image 3 As shown, the input skeleton only contains the two-dimensional coordinate information of 25 key points after preprocessing, such as figure 2 As shown, each skeleton sequence can be expressed as Among them, T=1000 and J=25, which respectively represent the time length of the skeleton sequence and the key point data of the skeleton.
[0067] After a preprocessing process including translation, normalization, and zero padding, the raw skeleton sequence data is input into a hierarchical limb attention LSTM for classification, and finally outputs the classification score for each frame of the skeleton sequence.
[0068] The implementation of the present invention comprises two parts: the training of the classification model (level limbs attention LSTM network) and the realization of the intelligent rehabilitation auxilia...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a spinal degenerative disease intelligent rehabilitation auxiliary training system based on deep learning. The system comprises a deep learning-based traditional Chinese medicine guidance video real-time classification module and a human skeleton representation-based video sequence division and evaluation module. The method comprises the following steps: acquiring two-dimensional human body skeleton data as training data of a learning model, and carrying out deep learning training to obtain a generalized deep learning model; obtaining a real-time frame classification result; and according to a frame classification result, carrying out segmentation and real-time error correction on skeleton sequences of the same category, and carrying out sequence comparison scoring on segmented sequence segments and expert group video skeleton sequence segments of the corresponding category. The system does not need guidance and intervention of medical staff, enables a patient to carry out traditional Chinese medicine guide operation training at any time, is suitable for families and basic medical and health institutions, can relieve the burden of the medical staff, and improves the flexibility and accuracy of rehabilitation training of the patient.
Description
technical field [0001] The invention belongs to the technical field of computer vision video understanding, in particular to a video sequence recognition and evaluation system based on deep learning. Background technique [0002] Daoyin of traditional Chinese medicine is a method of self-cultivation and treatment with Chinese characteristics. It promotes the recovery of limb movement by guiding patients to adjust shape based on mind adjustment and breath adjustment, that is, the main activities of the limbs. With the continuous development of computer hardware and artificial intelligence technology, the research and development of intelligent assisted rehabilitation training system has become a hot spot in related fields at home and abroad. In computer vision tasks, video behavior recognition is a very challenging field. The method based on RGB frame input often cannot meet the performance requirements of real-time processing. The method based on skeleton sequence has lower...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06V20/40G06V40/20G06N3/04G06N3/08
CPCG06N3/08G06N3/044
Inventor 路红沈梦琦杨博弘任浩然张文强李伟
Owner FUDAN UNIV