Squat Exercise Abnormality Detection by Analyzing Joint Angle for Knee Osteoarthritis Rehabilitation

Abstract

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.

The knowledge and self-management educational needs of older adults with knee osteoarthritis: A qualitative study

“…In addition to activities of daily living, the ability to participate in social and cultural activities concerned our study participants. From the Asian cultural perspective, kneeling and sitting cross-legged are customary practices in most of their traditional and social activities [53,54]. Participants who are unable to perform these movements voluntarily avoid these settings in order not to stand out or due to fear of being judge by or being a burden to others.…”

Mono Camera-based Human Skeletal Tracking for Squat Exercise Abnormality Detection using Double Exponential Smoothing

“…In comparison to prior systems, some researchers use depth cameras such as the Kinect sensor, a low-cost consumer-grade 3D camera, to extract key points on the human body [12]. This technology can contribute to the provision of several human action characteristics, such as depth, colour differentiation, and human skeletal structure [13].…”

“…[7] apply six machine learning frameworks; OpenPose, Tflite, Pifpat, Tfjs (mobileNet), Tfjs (Resnet 50), and BlazePose for pose estimation and correction of fitness training dataset since the goal was to find the fastest and most accurate methods that work in real-time. Besides that, the use of a Kinect sensor to extract the skeletal features has also been used to determine the abnormality of squat exercise from a dataset [12]. In addition, [15] and [16] suggested the use of the OpenPose framework to extract the keypoints coordinates from the RGB data for pose detection of fall action.…”

Healthcare Utilization and Knee Osteoarthritis Symptoms among Urban Older Malaysian

“…Knee OA was ranked as the 38th highest of 291 diseases in terms of overall burden measured by disability-adjusted life years [ 8 ]. Pain, mobility impairment, and physical inactivity are among the major consequences of knee OA that lead to functional limitation and dependency [ 9 , 10 , 11 , 12 , 13 ]. The symptoms burden associated with this chronic and disabling condition is expected to lead to increased healthcare utilization.…”