Autonomous gait event detection with portable single-camera gait kinematics analysis system

Cheng Yang, Ukadike C. Ugbolue, Andrew Kerr, Vladimir Stankovic, Lina Stankovic, Bruce Carse, Konstantinos T. Kaliarntas, Philip J. Rowe

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Laboratory-based non-wearable motion analysis systems have significantly advanced with robust objective measurement of the limb motion, resulting in quantified, standardized and reliable outcome measures compared with traditional, semi-subjective, observational gait analysis. However, the requirement for large laboratory space and operational expertise makes these system impractical for gait analysis at local clinics and homes. In this paper, we focus on autonomous gait event detection with our bespoke, relatively inexpensive, and portable, single-camera gait kinematics analysis system. Our proposed system includes video acquisition with camera calibration, Kalman-filter+StructuralSimilarity-based marker tracking, autonomous knee angle calculation, video-frame-identification-based autonomous gait event detection, and result visualization. The only operational effort required is the marker-template selection for tracking initialization, aided by an easy to use graphic user interface. The knee angle validation on 10 stroke patients and 5 healthy volunteers against a gold standard optical motion analysis system indicates very good agreement. The autonomous gait event detection shows high detection rates for all gait events. Experimental results demonstrate that the proposed system can automatically measure the knee angle and detect gait events with good accuracy, and thus offer an alternative, cost effective and convenient solution for clinical gait kinematics analysis.
LanguageEnglish
Article number5036857
Number of pages8
JournalJournal of Sensors
Volume2016
DOIs
Publication statusPublished - 5 Jan 2016

Fingerprint

gait
Gait analysis
systems analysis
Kinematics
kinematics
Cameras
cameras
Kalman filters
User interfaces
Visualization
Calibration
Costs
markers
space laboratories
Motion analysis
limbs
strokes
acquisition
templates
costs

Keywords

  • motion analysis system
  • video analytics
  • gait analysis

Cite this

@article{4c8a71fcdaa1406b893fd3504b951137,
title = "Autonomous gait event detection with portable single-camera gait kinematics analysis system",
abstract = "Laboratory-based non-wearable motion analysis systems have significantly advanced with robust objective measurement of the limb motion, resulting in quantified, standardized and reliable outcome measures compared with traditional, semi-subjective, observational gait analysis. However, the requirement for large laboratory space and operational expertise makes these system impractical for gait analysis at local clinics and homes. In this paper, we focus on autonomous gait event detection with our bespoke, relatively inexpensive, and portable, single-camera gait kinematics analysis system. Our proposed system includes video acquisition with camera calibration, Kalman-filter+StructuralSimilarity-based marker tracking, autonomous knee angle calculation, video-frame-identification-based autonomous gait event detection, and result visualization. The only operational effort required is the marker-template selection for tracking initialization, aided by an easy to use graphic user interface. The knee angle validation on 10 stroke patients and 5 healthy volunteers against a gold standard optical motion analysis system indicates very good agreement. The autonomous gait event detection shows high detection rates for all gait events. Experimental results demonstrate that the proposed system can automatically measure the knee angle and detect gait events with good accuracy, and thus offer an alternative, cost effective and convenient solution for clinical gait kinematics analysis.",
keywords = "motion analysis system, video analytics, gait analysis",
author = "Cheng Yang and Ugbolue, {Ukadike C.} and Andrew Kerr and Vladimir Stankovic and Lina Stankovic and Bruce Carse and Kaliarntas, {Konstantinos T.} and Rowe, {Philip J.}",
year = "2016",
month = "1",
day = "5",
doi = "10.1155/2016/5036857",
language = "English",
volume = "2016",
journal = "Journal of Sensors",
issn = "1687-725X",

}

Autonomous gait event detection with portable single-camera gait kinematics analysis system. / Yang, Cheng; Ugbolue, Ukadike C.; Kerr, Andrew; Stankovic, Vladimir; Stankovic, Lina; Carse, Bruce; Kaliarntas, Konstantinos T.; Rowe, Philip J.

In: Journal of Sensors, Vol. 2016, 5036857, 05.01.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Autonomous gait event detection with portable single-camera gait kinematics analysis system

AU - Yang, Cheng

AU - Ugbolue, Ukadike C.

AU - Kerr, Andrew

AU - Stankovic, Vladimir

AU - Stankovic, Lina

AU - Carse, Bruce

AU - Kaliarntas, Konstantinos T.

AU - Rowe, Philip J.

PY - 2016/1/5

Y1 - 2016/1/5

N2 - Laboratory-based non-wearable motion analysis systems have significantly advanced with robust objective measurement of the limb motion, resulting in quantified, standardized and reliable outcome measures compared with traditional, semi-subjective, observational gait analysis. However, the requirement for large laboratory space and operational expertise makes these system impractical for gait analysis at local clinics and homes. In this paper, we focus on autonomous gait event detection with our bespoke, relatively inexpensive, and portable, single-camera gait kinematics analysis system. Our proposed system includes video acquisition with camera calibration, Kalman-filter+StructuralSimilarity-based marker tracking, autonomous knee angle calculation, video-frame-identification-based autonomous gait event detection, and result visualization. The only operational effort required is the marker-template selection for tracking initialization, aided by an easy to use graphic user interface. The knee angle validation on 10 stroke patients and 5 healthy volunteers against a gold standard optical motion analysis system indicates very good agreement. The autonomous gait event detection shows high detection rates for all gait events. Experimental results demonstrate that the proposed system can automatically measure the knee angle and detect gait events with good accuracy, and thus offer an alternative, cost effective and convenient solution for clinical gait kinematics analysis.

AB - Laboratory-based non-wearable motion analysis systems have significantly advanced with robust objective measurement of the limb motion, resulting in quantified, standardized and reliable outcome measures compared with traditional, semi-subjective, observational gait analysis. However, the requirement for large laboratory space and operational expertise makes these system impractical for gait analysis at local clinics and homes. In this paper, we focus on autonomous gait event detection with our bespoke, relatively inexpensive, and portable, single-camera gait kinematics analysis system. Our proposed system includes video acquisition with camera calibration, Kalman-filter+StructuralSimilarity-based marker tracking, autonomous knee angle calculation, video-frame-identification-based autonomous gait event detection, and result visualization. The only operational effort required is the marker-template selection for tracking initialization, aided by an easy to use graphic user interface. The knee angle validation on 10 stroke patients and 5 healthy volunteers against a gold standard optical motion analysis system indicates very good agreement. The autonomous gait event detection shows high detection rates for all gait events. Experimental results demonstrate that the proposed system can automatically measure the knee angle and detect gait events with good accuracy, and thus offer an alternative, cost effective and convenient solution for clinical gait kinematics analysis.

KW - motion analysis system

KW - video analytics

KW - gait analysis

U2 - 10.1155/2016/5036857

DO - 10.1155/2016/5036857

M3 - Article

VL - 2016

JO - Journal of Sensors

T2 - Journal of Sensors

JF - Journal of Sensors

SN - 1687-725X

M1 - 5036857

ER -