Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification
Human body measurement data related to walking can characterize functional movement and thereby become an important tool for health assessment. Single-camera-captured two-dimensional (2D) image sequences of marker-less walking individuals might be a simple approach for estimating human body measurem...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/8/2836 |
_version_ | 1797537325373194240 |
---|---|
author | Tasriva Sikandar Mohammad F. Rabbi Kamarul H. Ghazali Omar Altwijri Mahdi Alqahtani Mohammed Almijalli Saleh Altayyar Nizam U. Ahamed |
author_facet | Tasriva Sikandar Mohammad F. Rabbi Kamarul H. Ghazali Omar Altwijri Mahdi Alqahtani Mohammed Almijalli Saleh Altayyar Nizam U. Ahamed |
author_sort | Tasriva Sikandar |
collection | DOAJ |
description | Human body measurement data related to walking can characterize functional movement and thereby become an important tool for health assessment. Single-camera-captured two-dimensional (2D) image sequences of marker-less walking individuals might be a simple approach for estimating human body measurement data which could be used in walking speed-related health assessment. Conventional body measurement data of 2D images are dependent on body-worn garments (used as segmental markers) and are susceptible to changes in the distance between the participant and camera in indoor and outdoor settings. In this study, we propose five ratio-based body measurement data that can be extracted from 2D images and can be used to classify three walking speeds (i.e., slow, normal, and fast) using a deep learning-based bidirectional long short-term memory classification model. The results showed that average classification accuracies of 88.08% and 79.18% could be achieved in indoor and outdoor environments, respectively. Additionally, the proposed ratio-based body measurement data are independent of body-worn garments and not susceptible to changes in the distance between the walking individual and camera. As a simple but efficient technique, the proposed walking speed classification has great potential to be employed in clinics and aged care homes. |
first_indexed | 2024-03-10T12:13:30Z |
format | Article |
id | doaj.art-7c5186e6c32e4ae4b6442c256c5e16a7 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T12:13:30Z |
publishDate | 2021-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-7c5186e6c32e4ae4b6442c256c5e16a72023-11-21T16:00:24ZengMDPI AGSensors1424-82202021-04-01218283610.3390/s21082836Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed ClassificationTasriva Sikandar0Mohammad F. Rabbi1Kamarul H. Ghazali2Omar Altwijri3Mahdi Alqahtani4Mohammed Almijalli5Saleh Altayyar6Nizam U. Ahamed7Faculty of Electrical and Electronics Engineering, Universiti Malaysia Pahang, Pekan 26600, MalaysiaSchool of Allied Health Sciences, Griffith University, Gold Coast, QLD 4222, AustraliaFaculty of Electrical and Electronics Engineering, Universiti Malaysia Pahang, Pekan 26600, MalaysiaBiomedical Technology Department, College of Applied Medical Sciences, King Saud University, Riyadh 11451, Saudi ArabiaBiomedical Technology Department, College of Applied Medical Sciences, King Saud University, Riyadh 11451, Saudi ArabiaBiomedical Technology Department, College of Applied Medical Sciences, King Saud University, Riyadh 11451, Saudi ArabiaBiomedical Technology Department, College of Applied Medical Sciences, King Saud University, Riyadh 11451, Saudi ArabiaNeuromuscular Research Laboratory/Warrior Human Performance Research Center, Department of Sports Medicine and Nutrition, University of Pittsburgh, Pittsburgh, PA 15203, USAHuman body measurement data related to walking can characterize functional movement and thereby become an important tool for health assessment. Single-camera-captured two-dimensional (2D) image sequences of marker-less walking individuals might be a simple approach for estimating human body measurement data which could be used in walking speed-related health assessment. Conventional body measurement data of 2D images are dependent on body-worn garments (used as segmental markers) and are susceptible to changes in the distance between the participant and camera in indoor and outdoor settings. In this study, we propose five ratio-based body measurement data that can be extracted from 2D images and can be used to classify three walking speeds (i.e., slow, normal, and fast) using a deep learning-based bidirectional long short-term memory classification model. The results showed that average classification accuracies of 88.08% and 79.18% could be achieved in indoor and outdoor environments, respectively. Additionally, the proposed ratio-based body measurement data are independent of body-worn garments and not susceptible to changes in the distance between the walking individual and camera. As a simple but efficient technique, the proposed walking speed classification has great potential to be employed in clinics and aged care homes.https://www.mdpi.com/1424-8220/21/8/28362D imagemarker-less videowalking speed patternwalking speed classificationquasi-periodic patternLSTM |
spellingShingle | Tasriva Sikandar Mohammad F. Rabbi Kamarul H. Ghazali Omar Altwijri Mahdi Alqahtani Mohammed Almijalli Saleh Altayyar Nizam U. Ahamed Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification Sensors 2D image marker-less video walking speed pattern walking speed classification quasi-periodic pattern LSTM |
title | Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification |
title_full | Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification |
title_fullStr | Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification |
title_full_unstemmed | Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification |
title_short | Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification |
title_sort | using a deep learning method and data from two dimensional 2d marker less video based images for walking speed classification |
topic | 2D image marker-less video walking speed pattern walking speed classification quasi-periodic pattern LSTM |
url | https://www.mdpi.com/1424-8220/21/8/2836 |
work_keys_str_mv | AT tasrivasikandar usingadeeplearningmethodanddatafromtwodimensional2dmarkerlessvideobasedimagesforwalkingspeedclassification AT mohammadfrabbi usingadeeplearningmethodanddatafromtwodimensional2dmarkerlessvideobasedimagesforwalkingspeedclassification AT kamarulhghazali usingadeeplearningmethodanddatafromtwodimensional2dmarkerlessvideobasedimagesforwalkingspeedclassification AT omaraltwijri usingadeeplearningmethodanddatafromtwodimensional2dmarkerlessvideobasedimagesforwalkingspeedclassification AT mahdialqahtani usingadeeplearningmethodanddatafromtwodimensional2dmarkerlessvideobasedimagesforwalkingspeedclassification AT mohammedalmijalli usingadeeplearningmethodanddatafromtwodimensional2dmarkerlessvideobasedimagesforwalkingspeedclassification AT salehaltayyar usingadeeplearningmethodanddatafromtwodimensional2dmarkerlessvideobasedimagesforwalkingspeedclassification AT nizamuahamed usingadeeplearningmethodanddatafromtwodimensional2dmarkerlessvideobasedimagesforwalkingspeedclassification |