Parkinson's disease finger tapping action recognition method and system, storage medium and terminal

Abstract

The invention provides a Parkinson's disease finger tapping action recognition method and system, a storage medium and a terminal. The Parkinson's disease finger tapping action recognition method comprises the following steps: acquiring video data including hand tapping actions of a Parkinson's disease patient; obtaining hand skeleton sequence data in the video data based on an OpenPose algorithm;constructing skeleton sequence features based on the hand skeleton sequence data; constructing a deep learning model for multi-stream fine-grained skeleton sequence action recognition based on the skeleton sequence features; and according to the deep learning model, identifying a to-be-identified finger tapping action. According to the Parkinson's disease finger tapping action recognition methodand system, the storage medium and the terminal, recognition of the Parkinson's disease finger tapping action is achieved based on the hand posture estimation algorithm and the deep learning algorithm, the accuracy is high, and the practicability is high.

Description

technical field [0001] The present invention relates to the technical field of action recognition, in particular to a method and system for recognizing Parkinson's disease finger tapping action, a storage medium and a terminal. Background technique [0002] Parkinson's Disease (PD) is one of the most common neurodegenerative diseases. It affects the motor system of the human body. The most obvious symptoms are tremor, stiffness, slow movement and difficulty in walking. In 2015, approximately 6.2 million people worldwide had Parkinson's disease and 117,400 died. Although there is no cure for Parkinson's disease, early diagnosis of the disease can help prolong the survival period of patients. In clinical diagnosis, doctors mainly judge the severity of motor symptoms in PD patients based on rating scales. The most commonly used rating scale is the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) revised by the Movement Disorders Society. MDS-UPDRS quantitatively evaluates...

AI Technical Summary

Problems solved by technology

[0011] (1) The solution based on wearable devices needs to spend a certain amount of capital costs and equipment debugging costs, and there is a lack of standardized wearing methods among different wearable devices, so it is not conducive to widespread clinical use;

[0012] (2) Traditional machine learning algorithms based on feature engineering usually require manual feature selection, while the manifestations of hand movement disorders in Parkinson's patients are relatively complex, and may be difficult to describe and characterize by extracting simple features;

[0013] (3) For the hand tapping test, there are only subtle differences in the performance of different severity levels, and this fine-grained classification problem poses a challenge for an accurate automatic evaluation system;

[0014] (4) The problem of unbalanced data categories in clinical data collection makes it difficult to improve the accuracy of category recognition with a small number of samples

Images