Multiple Kinect based system to monitor and analyze key performance indicators of physical training

Karolis Ryselis,Robertas Damaševičius,Rytis Maskeliūnas,Tomas Blažauskas,Tautvydas Petkus

doi:10.1186/s13673-020-00256-4

Karolis Ryselis, Robertas Damaševičius + Show 3 more

Open Access

https://doi.org/10.1186/s13673-020-00256-4

Copy DOI

Abstract

Using a single Kinect device for human skeleton tracking and motion tracking lacks of reliability required in sports medicine and rehabilitation domains. Human joints reconstructed from non-standard poses such as squatting, sitting and lying are asymmetric and have unnatural lengths while their recognition error exceeds the error of recognizing standard poses. In order to achieve higher accuracy and usability for practical smart health applications we propose a practical solution for human skeleton tracking and analysis that performs the fusion of skeletal data from three Kinect devices to provide a complete 3D spatial coverage of a subject. The paper describes a novel data fusion algorithm using algebraic operations in vector space, the deployment of the system using three Kinect units, provides analysis of dynamic characteristics (position of joints, speed of movement, functional working envelope, body asymmetry and the rate of fatigue) of human motion during physical exercising, and evaluates intra-session reliability of the system using test–retest reliability metrics (intra-class correlation, coefficient of variation and coefficient of determination). Comparison of multi-Kinect system vs single-Kinect system shows an improvement in accuracy of 15.7%, while intra-session reliability is rated as excellent.

Highlights

Physical training is an effective tool for health diagnostics, rehabilitation, and prevention of unwanted health problems such as obesity, hypertension or Parkinson’s disease [2, 49, 58]
Motivation can be increased by exergames, which employ the advances in virtual reality, sensory and motion tracking technologies [17, 37, 41]
Normalized mean limb length (NML) is the mean value of the length of each body limb Lmean divided by its maximum value Lmax

Summary

Introduction

Physical training is an effective tool for health diagnostics, rehabilitation, and prevention of unwanted health problems such as obesity, hypertension or Parkinson’s disease [2, 49, 58]. Kinetic therapy sessions can help both healthy people and people with motor dysfunctions to improve their control, strength, skills and the range of motion [22]. Older and disabled people may have difficulties attending physical training sessions outside of their homes, while they rarely perform enough exercises at home due to low motivation. Motivation can be increased by exergames, which employ the advances in virtual reality, sensory and motion tracking technologies [17, 37, 41]. Motion sensor technology can be employed to monitor certain elements of physical training and provide motivation by a virtual personal trainer [62]. Analysis of human skeleton data in motion can be used to provide feedback on the incorrect body posture [59] or incorrect

Objectives

Methods

Results

Discussion

Conclusion