Improved kinect-based spatiotemporal and kinematic treadmill gait assessment

Eltoukhy, Moataz; Oh, Jeong-Hoon; Kuenze, Christopher; Signorile, Joseph F.

doi:10.1016/j.gaitpost.2016.10.001

Cited by 124 publications

(105 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Kinect is a cost-effective device that has excellent measurement properties when compared with the criterion standard 3-dimensional motion capture. 39 The efficacy of this method has shown great potential for implementation in a variety of clinical and sport-specific environments, improving participant engagement and compliance. 20 In addition, enhancing corrective exercises in this manner reduces the need for constant clinician oversight and offers the user specific and individualized feedback.…”

Section: Discussionmentioning

confidence: 99%

Visual Biofeedback and Changes in Lower Extremity Kinematics in Individuals With Medial Knee Displacement

Marshall

Hertel

Hart

et al. 2020

Journal of Athletic Training

View full text Add to dashboard Cite

Context Increased frontal-plane knee motion during functional tasks, or medial knee displacement, is a predictor of noncontact anterior cruciate ligament injury and patellofemoral pain. Intervention studies that resulted in a reduced risk of knee injury included some form of feedback to address aberrant lower extremity movement patterns. Research on integrating feedback into single-legged tasks and the ability to train 1 task and test another is limited. Objective To determine if adding real-time visual biofeedback to common lower extremity exercises would improve single-legged landing mechanics in females with medial knee displacement. Design Cohort study. Setting University laboratory. Patients or Other Participants Twenty-four recreationally active females with medial knee displacement were randomized to a visual-biofeedback group (n = 12; age = 19.75 ± 0.87 years, height = 165.32 ± 8.69 cm, mass = 62.41 ± 8.91 kg) or a control group (n = 12; age = 19.75 ± 0.97 years, height = 166.98 ± 6.89 cm, mass = 59.98 ± 6.24 kg). Intervention(s) Individuals in the feedback group viewed a real-time digital model of their body segments generated by Microsoft Kinect. The skeletal model changed color according to the knee-abduction angle of the test limb during the exercise tasks. Main Outcome Measure(s) Participants completed 3 trials of the single-legged drop vertical jump (SL-DVJ) while triplanar kinematics at the trunk, hip, knee, and ankle were collected via 3-dimensional motion capture. The feedback and control groups completed lower extremity exercises with or without real-time visual biofeedback, respectively. After the intervention, participants completed 3 additional trials of the SL-DVJ. Results At baseline, the feedback group had 3.83° more ankle eversion than the control group after initial contact. After the intervention, the feedback group exhibited 13.03° more knee flexion during the flight phase of the SL-DVJ and 6.16° less knee abduction after initial contact than the control group. The feedback group also demonstrated a 3.02° decrease in peak knee-abduction excursion compared with the baseline values (P = .008). Conclusions Real-time visual biofeedback immediately improved faulty lower extremity kinematics related to knee-injury risk. Individuals with medial knee displacement adjusted their movement patterns after a single training session and reduced their medial knee motion during a dynamic task.

show abstract

Section: Discussionmentioning

confidence: 99%

Visual Biofeedback and Changes in Lower Extremity Kinematics in Individuals With Medial Knee Displacement

Marshall

Hertel

Hart

et al. 2020

Journal of Athletic Training

View full text Add to dashboard Cite

show abstract

“…Several low-cost systems exist that use a single-camera setup, footswitches, accelerometers, gyroscopes, and inertial measurement units; however, results on the accuracy of spatial parameters are inconsistent or absent and it is questionable whether some of these systems are reliable in persons with gait deviations (e.g. forefoot contact at initial contact) (19)(20)(21)(22)(23)(24)(25)(26)(27)(28)(29)(30).…”

mentioning

confidence: 99%

Concurrent validity and reliability of a low-cost gait analysis system for assessment of spatiotemporal gait parameters

Bloemendaal¹,

Beelen²,

Kleissen³

et al. 2019

J Rehabil Med

View full text Add to dashboard Cite

Gait parameters, such as step length and step time, allow the quantification of gait deviations in persons with various diseases. Treatment can be customized and evaluated based on these parameters. However, few lowcost, easily applicable systems are available for clinical settings to accurately measure gait parameters. A lowcost spatiotemporal gait analysis system was developed and this study evaluated its accuracy and reliability. The spatiotemporal gait analysis system consists of a camera placed perpendicular to the walkway, which can be used stationary or moved manually along a parallel rail system to capture multiple strides of an individual during a single walk. Thirty-three healthy adults completed trials of barefoot, toe and shod walking. These adults were simultaneously recorded using an electronic walkway, the GAITRite®, for comparison. The results showed that the spatiotemporal gait analysis system is an accurate and reliable system to assess step and stride length, step, stance, and stride time, but not to assess double support and swing time. Objective: To determine the concurrent validity and reliability of a low-cost spatiotemporal gait analysis system for clinical use in rehabilitation medicine. Design: Cross-sectional study. Subjects: Thirty-three healthy adults. Methods: The spatiotemporal gait analysis system consists of a video camera placed perpendicular to a 10-m walkway and calibrated for spatial reference. The conditions evaluated in this study were: barefoot walking at comfortable and slow speed, toe and shod walking using a stationary camera setup and barefoot walking at comfortable speed using a moving camera setup. The GAITRite® was used as reference. Results: High intraclass correlation coefficients (ICC≥ 0.97; 95% lower limit confidence intervals (95% CIs) ≥ 0.77) were found between systems for step and stride length, and step, stance and stride time, across setups and conditions. Standard error of measurement and Bland-Altman repeatability coefficients were ≤ 2.4% and ≤ 6.3%, respectively. A minimum of 4 footsteps was required to obtain ICC >0.90 and coefficient of variation < 10%. For double support and swing time, ICCs were generally low (ICC≥ 0.21). Inter-rater reliability was excellent for step length, step and stance time (ICC≥ 0.94; lower limit 95% CIs ≥ 0.86). Conclusion: The spatiotemporal gait analysis system is valid and reliable for assessing spatiotemporal parameters in different walking conditions. However, the validity of double support and swing time could not be confirmed.

show abstract

“…These characteristics of the data collection conditions differ significantly from real-world walking, the majority of which is performed on inconsistent, rough surfaces with obstacles and turns to negotiate. Depth sensorbased technologies such as the Microsoft Kinect TM present another solution to collecting spatiotemporal gait data in clinical settings, and their validity has been demonstrated for several scenarios including overground walking (Müller et al, 2017), treadmill walking (Eltoukhy et al, 2017), and stair ambulation (Oh et al, 2018). However, depth sensors have a relatively short range of 3.5m and their ability to handle occlusions is limited, reducing the environments in which they can be used (Clark et al, 2013;Sarsfield et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Assessment of spatiotemporal gait parameters using a deep learning algorithm-based markerless motion capture system

Kanko¹,

Strutzenberger²,

Brown³

et al. 2020

Preprint

View full text Add to dashboard Cite

Spatiotemporal parameters can characterize the gait patterns of individuals, allowing assessment of their health status and detection of clinically meaningful changes in their gait. Video-based markerless motion capture is a user-friendly, inexpensive, and widely applicable technology that could reduce the barriers to measuring spatiotemporal gait parameters in clinical and more diverse settings. The aim of this work was to determine whether spatiotemporal gait parameters measured using Theia3D markerless motion capture demonstrate concurrent validity with those measured using marker-based motion capture. Thirty healthy adult participants performed treadmill walking at self-selected speeds while 2D video and marker-based motion capture data were collected simultaneously. Kinematic-based gait events were used to measure nine spatiotemporal gait parameters from both systems independently. The parameters were compared using their group means, Bland-Altman methods, Pearson correlation coefficients, paired-samples t-tests, and intraclass correlation coefficients (ICC(A-1) and ICC(C-1)). Group means between systems were indistinguishable across all nine gait parameters, and the Bland-Altman plots showed no systematic biases or clinically meaningful differences between the systems. Pearson coefficients indicated near-perfect correlations (r ≥0.96) between systems for all but two parameters, which had strong correlations (double-limb support time, r=0.87; swing time, r=0.88). T-tests indicated differences in stance, swing, and double-limb support time parameters, but strong correlations were found for all ICCs, the lowest being 0.84 for both double-limb support time and swing time. The measurements made by the Theia3D markerless motion capture system demonstrated concurrent validity with those from the marker-based system, indicating sufficient accuracy for research, clinical, and other uses.

show abstract

Improved kinect-based spatiotemporal and kinematic treadmill gait assessment

Cited by 124 publications

References 26 publications

Visual Biofeedback and Changes in Lower Extremity Kinematics in Individuals With Medial Knee Displacement

Visual Biofeedback and Changes in Lower Extremity Kinematics in Individuals With Medial Knee Displacement

Concurrent validity and reliability of a low-cost gait analysis system for assessment of spatiotemporal gait parameters

Assessment of spatiotemporal gait parameters using a deep learning algorithm-based markerless motion capture system

Contact Info

Product

Resources

About