Normally, osteoarthritic knee patients experienced 1) difficulties controlling their fine motors, 2) lack of muscle strength, and 3) limited range of motion. The limitations can be improved by physiotherapy exercises to 1) enhance flexibility and mobility of joints and 2) increase strength and endurance of the muscles. However, the patients should be individually monitored so that the exercises are performed correctly, effectively and efficiently. This paper focuses on squat exercise monitoring for knee osteoarthritis rehabilitation. The patient’s movement is captured by using a low cost 3D camera, Kinect sensor for skeletal tracking to recognize and track people without using marker. 3D coordinates of each joint is retrieved from the skeleton data, where a joint angle is derived based on two intersecting human body segments. Time series of the joint angles during the squat exercise are recorded, which are then smoothed by Double Exponential Smoothing technique to find the variability between them. The proposed method is validated by using simulated videos of squat exercise performed by 10 healthy volunteers of various physiques and gender to simulate the normal and abnormal conditions. Mean Squared Error (MSE) is calculated between the measured and smoothed angles to classify the movement either normal or abnormal. The parameters for smoothing and trend control used are 0.8928 and 0.7256, respectively, which are derived based on optimal MSE of the 10 volunteers. The simulation results show that the average MSE for each 10 samples of normal and abnormal conditions are 3.1358 and 10.5205, respectively. Hence, a simple threshold method has been developed to detect movement abnormality while doing squat exercise.
Human action analysis is an enthralling area of research in artificial intelligence, as it may be used to improve a range of applications, including sports coaching, rehabilitation, and monitoring. By forecasting the body's vital position of posture, human action analysis may be performed. Human body tracking and action recognition are the two primary components of video-based human action analysis. We present an efficient human tracking model for squat exercises using the open-source MediaPipe technology. The human posture detection model is used to detect and track the vital body joints within the human topology. A series of critical body joint motions are being observed and analysed for aberrant body movement patterns while conducting squat workouts. The model is validated using a squat dataset collected from ten healthy people of varying genders and physiques. The incoming data from the model is filtered using the double exponential smoothing method;the Mean Squared Error between the measured and smoothed angles is determined to classify the movement as normal or abnormal. Level smoothing and trend control have parameters of 0.8928 and 0.77256, respectively. Six out of ten subjects in the trial were precisely predicted by the model. The mean square error of the signals obtained under normal and abnormal squat settings is 56.3197 and 29.7857, respectively. Thus, by utilising a simple threshold method, the low-cost camera-based squat movement condition detection model was able to detect the abnormality of the workout movement.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.