The purpose of this study was to assess the Openpose reliability to measure kinematics and spatiotemporal gait parameters and to evaluate the minimum technical requirements. This analysis used video and optoelectronic motion capture simultaneously recorded. We assessed more of 20 subject with different motor gait impairments
Marker-based Optical motion tracking is the gold standard in gait analysis, but today, markerless solutions are growing rapidly. Treatment of physical impairments could improve if supported with reliable motion capture. Moreover, the use of markerless technology offers numerous advantages for working with pediatric populations under various conditions. In this paper, we assess the Openpose reliability to measure kinematics and spatiotemporal gait parameters and to evaluate the minimum technical requirements., in a population of children with and without gait impairments. Validating markerless methods can open the way for new motion capture techniques and enhance the accessibility of kinematic measurements and improve the treatment of physical impairments.
Study Type
OBSERVATIONAL
Enrollment
25
The raw data acquired from motion capture system were processed with Smart Analyzer software (BTS Bioengineering, Milano, Italy). First, the 3D data were filtered and interpolated in case of missing data for short time. Then spatial-temporal parameters (cycle duration, cadence, gait speed, stance phase, swing phase, double-support phase, stride length and step width) and conventional kinematic parameters of traditional Davis marker-set protocols were computed.
The two videos were elaborated using OpenPose that returns a set of 25 2D keypoints coordinates for body pose estimation for each video. Key-points were located in relevant body landmarks and it were used to determine the 2D Cartesian coordinates on the sagittal plane and on the frontal plane. The data calculated with routines were filtered and interpolated in case of missing data. With respect to kinematic parameters, the segment and joint angles were measured from the estimated feature points of each joint. Spatiotemporal gait parameters were calculated using successive heel strike and toe-off events.
IRCCS E. Medea
Bosisio Parini, Italy, Italy
Absolute Error
Absolute errors were calculated for the kinematics parameters and for each spatiotemporal variable by taking the absolute value after subtracting the values obtained using pose estimation methods from the value measured using markerbased motion capture
Time frame: Through study completion, an average of 1 year
intraclass correlation coefficients
To confirm whether the data obtained by OpenPose agreed with the data from the optoelectronic system, investigators calculated the ICCs (two-way mixed effects model, absolute agreement, average measurements) between the spatiotemporal and kinematic data from both systems. The ICC values were interpreted as follows: poor agreement for ICC \< 0.5, moderate agreement for values between 0.5 and 0.75, good agreement for values between 0.75 and 0.9, and excellent agreement for values greater than 0.90.
Time frame: Through study completion, an average of 1 year
cross-correlation coefficients
The cross-correlation coefficients (CCC) between both systems were used to evaluate the similarity of angles during the gait cycle. The CCC values were interpreted as follows: weak or no coupling for values between -0.3 and 0.3, moderate coupling for values between 0.3 and 0.7 or -0.7 and -0.3, and strong coupling for values greater than 0.7 or less than -0.7.
Time frame: Through study completion, an average of 1 year
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.