Automation enhancement and accuracy investigation of a portable single-camera gait analysis system

C. Yang, U.C. Ugbolue, D. McNicol, V. Stankovic, L. Stankovic, A. Kerr, B. Carse, K.T. Kaliarntas, P.J. Rowe

Research output: Contribution to journalArticle

Abstract

While optical motion analysis systems can provide high-fidelity gait parameters, they are usually impractical for local clinics and home use, due to high cost, requirement for large space, and lack of portability. In this study, we focus on a cost-effective and portable, single-camera gait analysis solution, based on video acquisition with calibration, autonomous detection of frames-of-interest,
Kalman-filter+Structural-Similarity-based marker tracking, and autonomous knee angle calculation. The proposed system is tested using 15 participants, including 10 stroke patients and 5 healthy volunteers. The evaluation of autonomous frames-of-interest detection shows only 0.2% difference between the frame number of the detected frame compared to the frame number of the manually labelled ground truth frame, and thus can replace manual labelling. The system is validated against a gold standard optical motion analysis system, using knee angle accuracy as metric of assessment. The accuracy investigation between the RGBand the grayscale-video marker tracking schemes shows that the grayscale system suffers from negligible accuracy loss with a significant processing speed advantage. Experimental results demonstrate that the proposed system can automatically estimate the knee angle, with R-squared value larger than 0.95 and Bland-Altman plot results smaller than 3.0127 degrees mean error.
LanguageEnglish
Number of pages9
JournalIET Science, Measurement & Technology
Early online date21 Jan 2019
DOIs
StateE-pub ahead of print - 21 Jan 2019

Fingerprint

Gait analysis
Automation
Cameras
Kalman filters
Labeling
Costs
Calibration
Processing
Motion analysis

Cite this

Yang, C. ; Ugbolue, U.C. ; McNicol, D. ; Stankovic, V. ; Stankovic, L. ; Kerr, A. ; Carse, B. ; Kaliarntas, K.T. ; Rowe, P.J. . / Automation enhancement and accuracy investigation of a portable single-camera gait analysis system. In: IET Science, Measurement & Technology. 2019
@article{29ccbe1a30d54a57ac7ed6981e740660,
title = "Automation enhancement and accuracy investigation of a portable single-camera gait analysis system",
abstract = "While optical motion analysis systems can provide high-fidelity gait parameters, they are usually impractical for local clinics and home use, due to high cost, requirement for large space, and lack of portability. In this study, we focus on a cost-effective and portable, single-camera gait analysis solution, based on video acquisition with calibration, autonomous detection of frames-of-interest,Kalman-filter+Structural-Similarity-based marker tracking, and autonomous knee angle calculation. The proposed system is tested using 15 participants, including 10 stroke patients and 5 healthy volunteers. The evaluation of autonomous frames-of-interest detection shows only 0.2\{%} difference between the frame number of the detected frame compared to the frame number of the manually labelled ground truth frame, and thus can replace manual labelling. The system is validated against a gold standard optical motion analysis system, using knee angle accuracy as metric of assessment. The accuracy investigation between the RGBand the grayscale-video marker tracking schemes shows that the grayscale system suffers from negligible accuracy loss with a significant processing speed advantage. Experimental results demonstrate that the proposed system can automatically estimate the knee angle, with R-squared value larger than 0.95 and Bland-Altman plot results smaller than 3.0127 degrees mean error.",
author = "C. Yang and U.C. Ugbolue and D. McNicol and V. Stankovic and L. Stankovic and A. Kerr and B. Carse and K.T. Kaliarntas and P.J. Rowe",
year = "2019",
month = "1",
day = "21",
doi = "10.1049/iet-smt.2018.5246",
language = "English",
journal = "IET Science, Measurement & Technology",
issn = "1751-8822",
publisher = "IET",

}

Automation enhancement and accuracy investigation of a portable single-camera gait analysis system. / Yang, C.; Ugbolue, U.C.; McNicol, D.; Stankovic, V.; Stankovic, L.; Kerr, A.; Carse, B.; Kaliarntas, K.T.; Rowe, P.J. .

In: IET Science, Measurement & Technology, 21.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automation enhancement and accuracy investigation of a portable single-camera gait analysis system

AU - Yang,C.

AU - Ugbolue,U.C.

AU - McNicol,D.

AU - Stankovic,V.

AU - Stankovic,L.

AU - Kerr,A.

AU - Carse,B.

AU - Kaliarntas,K.T.

AU - Rowe,P.J.

PY - 2019/1/21

Y1 - 2019/1/21

N2 - While optical motion analysis systems can provide high-fidelity gait parameters, they are usually impractical for local clinics and home use, due to high cost, requirement for large space, and lack of portability. In this study, we focus on a cost-effective and portable, single-camera gait analysis solution, based on video acquisition with calibration, autonomous detection of frames-of-interest,Kalman-filter+Structural-Similarity-based marker tracking, and autonomous knee angle calculation. The proposed system is tested using 15 participants, including 10 stroke patients and 5 healthy volunteers. The evaluation of autonomous frames-of-interest detection shows only 0.2% difference between the frame number of the detected frame compared to the frame number of the manually labelled ground truth frame, and thus can replace manual labelling. The system is validated against a gold standard optical motion analysis system, using knee angle accuracy as metric of assessment. The accuracy investigation between the RGBand the grayscale-video marker tracking schemes shows that the grayscale system suffers from negligible accuracy loss with a significant processing speed advantage. Experimental results demonstrate that the proposed system can automatically estimate the knee angle, with R-squared value larger than 0.95 and Bland-Altman plot results smaller than 3.0127 degrees mean error.

AB - While optical motion analysis systems can provide high-fidelity gait parameters, they are usually impractical for local clinics and home use, due to high cost, requirement for large space, and lack of portability. In this study, we focus on a cost-effective and portable, single-camera gait analysis solution, based on video acquisition with calibration, autonomous detection of frames-of-interest,Kalman-filter+Structural-Similarity-based marker tracking, and autonomous knee angle calculation. The proposed system is tested using 15 participants, including 10 stroke patients and 5 healthy volunteers. The evaluation of autonomous frames-of-interest detection shows only 0.2% difference between the frame number of the detected frame compared to the frame number of the manually labelled ground truth frame, and thus can replace manual labelling. The system is validated against a gold standard optical motion analysis system, using knee angle accuracy as metric of assessment. The accuracy investigation between the RGBand the grayscale-video marker tracking schemes shows that the grayscale system suffers from negligible accuracy loss with a significant processing speed advantage. Experimental results demonstrate that the proposed system can automatically estimate the knee angle, with R-squared value larger than 0.95 and Bland-Altman plot results smaller than 3.0127 degrees mean error.

U2 - 10.1049/iet-smt.2018.5246

DO - 10.1049/iet-smt.2018.5246

M3 - Article

JO - IET Science, Measurement & Technology

T2 - IET Science, Measurement & Technology

JF - IET Science, Measurement & Technology

SN - 1751-8822

ER -