arrow
Return

Gyroscope-Driven Virtual Replication: Enhancing Human Movement Analysis

delete2026-01-01
delete0
PRE
AI
P
Patrick B. N. Alvim *
J
Jonathan C. F. da Silva
V
Vicente J. P. Amorim
R
Ricardo Santos
M
Mateus Silva
R
Ricardo Oliveira
DOI:10.1007/978-3-032-08570-2_9delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Accurately replicating real-world activities in a virtual environment is essential for advancing innovations in simulations, training, and data analysis. This capability is particularly valuable for performing tasks that are challenging, risky, or impractical in real life, thereby enabling comprehensive studies without compromising safety or feasibility. In this context, capturing and analyzing real-world data within a virtual environment allows for the detailed reproduction of actions and a deeper understanding of their implications. This paper presents a system designed for capturing and virtually replicating walking and running activities by leveraging gyroscope data to monitor the rotational movements of the lower limbs. Our approach ensures precise replication of these movements, facilitating detailed biomechanical analysis. Our results demonstrate that using specialized sensors, as opposed to general-purpose devices like smartwatches, yields more accurate and localized data, enhancing the granularity of movement analysis. Additionally, we review the use of multimodal data specifically the integration of motion sensors and image analysis for human activity recognition. Although this integration is not yet part of our current system, the review will guide future improvements to enhance the accuracy and scope of human activity recognition in virtual environments. Our system lays the groundwork for the development of advanced devices for human data capture and proposes a communication interface between the real and virtual realms, supporting in-depth studies on movement biomechanics with potential applications in sports science and orthopedics.
Keywords:
Sensors
Wearable
App
Mobile
AI

Journal

E
ENTERPRISE INFORMATION SYSTEMS, ICEIS 2024, PT I
IF:
0
Papers:
21
Citations:
0

Organization

U
Universidade Federal de Ouro Preto
Scholars:
3.2K
Papers: 2.2K
Citations: 1.6K
Cited Papers

Cited Papers

Wearables for Running Gait Analysis: A Systematic Review
err2022-10-15
err53
errOAAI
errMason, Rachel; Pearson, Liam T.; Barry, Gillian; Young, Fraser; Lennon, Oisin; Godfrey, Alan; Stuart, Samuel
errShare
errSave
Balance control during gait initiation: State-of-the-art and research perspectives
err2017-11-18
err0
errOAAI
errEric Yiou; Teddy Caderby; Arnaud Delafontaine; Paul Fourcade; Jean-Louis Honeine
errShare
errSave
Long Short-Term Memory
err1997-11-01
err0
PREAI
errSepp Hochreiter; Jürgen Schmidhuber
errShare
errSave
A vision-based approach for fall detection using multiple cameras and convolutional neural networks: A case study using the UP-Fall detection dataset
err2019-12-01
err86
PREAI
errEspinosa, Ricardo; Ponce, Hiram; Gutierrez, Sebastian; Martinez-Villasenor, Lourdes; Brieva, Jorge; Moya-Albor, Ernesto
errShare
errSave
errShare
errSave
Center of gravity dynamic stability in normal and vestibulopathic gait
err1998-10-01
err0
errOAAI
errCarole A Tucker; Jose Ramirez; David E Krebs; Patrick O Riley
errShare
errSave
The Study of Drunken Abnormal Human Gait Recognition using Accelerometer and Gyroscope Sensors in Mobile Application
err2020-02-01
err0
PREAI
errTirra Hanin Mohd Zaki; Musab Sahrim; Juliza Jamaludin; Sharma Rao Balakrishnan; Lily Hanefarezan Asbulah; Filzah Syairah Hussin
errShare
errSave
Vision-based human activity recognition: a survey
err2020-08-15
err258
errOAAI
errBeddiar, Djamila Romaissa; Nini, Brahim; Sabokrou, Mohammad; Hadid, Abdenour
errShare
errSave
Sensor-to-Segment Calibration Methodologies for Lower-Body Kinematic Analysis with Inertial Sensors: A Systematic Review
errSENSORS
IF3.5
err2020-06-11
err52
errOAAI
errPacher, Leonie; Chatellier, Christian; Vauzelle, Rodolphe; Fradet, Laetitia
errShare
errSave
researcher View more