Human body balance ability classification method based on three-dimensional convolutional neural network

Abstract

The invention discloses a human body balance ability classification method based on a three-dimensional convolutional neural network. The method is specifically implemented according to the followingsteps: step 1, shooting human body walking posture videos of a normal person and an abnormal person in a built virtual scene simulating reality; 2, respectively extracting the walking posture videos of the normal person and the abnormal person collected in the step 1 into images, respectively training the images of the normal person and the abnormal person in a three-dimensional convolutional neural network, and calculating feature vectors; and 3, inputting the feature vector obtained in the step 2 into a Softmax function, and classifying the balance ability by utilizing a numerical value obtained by the Softmax function, so that the problem of low classification accuracy caused by single extracted feature in the prior art is solved.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and relates to a method for classifying human body balance ability based on a three-dimensional convolutional neural network. Background technique [0002] The ability to balance can cause not only physical trauma, but psychological trauma as well. Falls can cause people to show negativity, fear, depression, and resistance to new things. These behaviors will not only limit their activities, but also lose self-confidence, which is extremely detrimental to people's physical and mental health. Possessing a good balance ability is conducive to improving the function of motor organs and vestibular organs, improving the central nervous system's regulation of muscle tissue and internal organs, thereby ensuring the smooth progress of physical activities, improving the ability to adapt to complex environments and self-protection Ability. [0003] The traditional methods of subjective human balance...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a human body balance ability classification method based on a three-dimensional convolutional neural network, which solves the problem in the prior art that the extracted features are single, resulting in low classification accuracy

Images