Previous Article in Journal
DLCPD-25: A Large-Scale and Diverse Dataset for Crop Disease and Pest Recognition
Previous Article in Special Issue
Walking Stability and Kinematic Variability Following Motor Fatigue Induced by Incline Treadmill Walking
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sensors
Volume 25
Issue 22
10.3390/s25227100
sensors-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

RecovGait: Occluded Parkinson’s Disease Gait Reconstruction Using Unscented Tracking with Gated Initialization Technique

by
Chiau Wen Yeong
1,
Tee Connie
1,2,*,
Thian Song Ong
1,3,
Nor Izzati Saedon
4,
Ahmad Al-Khatib
5 and
Mahmoud Farfoura
5
1
Faculty of Information Science and Technology, Multimedia University Melaka, Melaka 75450, Malaysia
2
Centre for Image and Vision Computing, COE for Advanced Cloud, Multimedia University, Melaka 75450, Malaysia
3
Centre for Advanced Analytics, COE for Artificial Intelligence, Multimedia University, Melaka 75450, Malaysia
4
Department of Medicine, Faculty of Medicine, Universiti Malaya, Kuala Lumpur 50603, Malaysia
5
Faculty of Science and Information Technology, Al-Zaytoonah University of Jordan, Amman 11733, Jordan
*
Author to whom correspondence should be addressed.
Sensors 2025, 25(22), 7100; https://doi.org/10.3390/s25227100 (registering DOI)
Submission received: 6 October 2025 / Revised: 12 November 2025 / Accepted: 18 November 2025 / Published: 20 November 2025
(This article belongs to the Collection Sensors for Gait, Posture, and Health Monitoring)
Versions Notes

Abstract

Parkinson’s disease is a neurodegenerative disorder disease that worsens over time and involves the deterioration of nerve cells in the brain. Gait analysis has emerged as a promising tool for early detection and monitoring of Parkinson’s disease. However, the accurate classification of Parkinsonian gait is often compromised by missing body keypoints, particularly in critical regions like the hip and legs that are important for motion analysis. In this study, we propose RecovGait, a novel method that combines a gated initialization technique with unscented tracking to recover missing human body keypoints. The gated initialization provides initial estimates, which are subsequently refined through unscented tracking to enhance reconstruction accuracy. Our findings show that missing keypoints in the hips and legs significantly affect the classification result, with accuracy dropping from 0.8043 to 0.5217 in these areas. By using the gated initialization with an unscented tracking method to recover these occluded keypoints, we achieve an MAPE value as low as 0.4082. This study highlights the impact of hip and leg keypoints on Parkinson’s disease gait classification and presents a robust solution for mitigating the challenges posed by occlusions in real-world scenarios.
Keywords: Parkinson’s disease; computer vision; occlusion; AlphaPose; unscented tracking; gated initialization Parkinson’s disease; computer vision; occlusion; AlphaPose; unscented tracking; gated initialization

Share and Cite

MDPI and ACS Style

Yeong, C.W.; Connie, T.; Ong, T.S.; Saedon, N.I.; Al-Khatib, A.; Farfoura, M. RecovGait: Occluded Parkinson’s Disease Gait Reconstruction Using Unscented Tracking with Gated Initialization Technique. Sensors 2025, 25, 7100. https://doi.org/10.3390/s25227100

AMA Style

Yeong CW, Connie T, Ong TS, Saedon NI, Al-Khatib A, Farfoura M. RecovGait: Occluded Parkinson’s Disease Gait Reconstruction Using Unscented Tracking with Gated Initialization Technique. Sensors. 2025; 25(22):7100. https://doi.org/10.3390/s25227100

Chicago/Turabian Style

Yeong, Chiau Wen, Tee Connie, Thian Song Ong, Nor Izzati Saedon, Ahmad Al-Khatib, and Mahmoud Farfoura. 2025. "RecovGait: Occluded Parkinson’s Disease Gait Reconstruction Using Unscented Tracking with Gated Initialization Technique" Sensors 25, no. 22: 7100. https://doi.org/10.3390/s25227100

APA Style

Yeong, C. W., Connie, T., Ong, T. S., Saedon, N. I., Al-Khatib, A., & Farfoura, M. (2025). RecovGait: Occluded Parkinson’s Disease Gait Reconstruction Using Unscented Tracking with Gated Initialization Technique. Sensors, 25(22), 7100. https://doi.org/10.3390/s25227100

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop