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

• Published in: International journal of advanced computer science & applications Vol. 13; no. 7
• Main Authors: Hisham, Muhammad Nafis, Hassan, Mohd Fadzil Abu, Ibrahim, Norazlin, Zin, Zalhan Mohd
• Format: Journal Article
• Language: English
• Published: West Yorkshire Science and Information (SAI) Organization Limited 01.01.2022
• Subjects: Algorithms; Artificial intelligence; Automation; Cameras; Computer science; COVID-19; Datasets; Error analysis; Exercise; Fitness training programs; Human body; Human mechanics; Human performance; Machine learning; Motion perception; Movement; Older people; Physical fitness; Posture; Rehabilitation; Sensors; Smoothing; Sports injuries; Sports training; Topology; Tracking
• ISSN: 2158-107X; 2156-5570
• DOI: 10.14569/IJACSA.2022.0130709

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.