Validation of the Microsoft Kinect® camera system for measurement of lower extremity jump landing and squatting kinematics

Abstract

Cost effective, quantifiable assessment of lower extremity movement represents potential improvement over standard tools for evaluation of injury risk. Ten healthy participants completed three trials of a drop jump, overhead squat, and single leg squat task. Peak hip and knee kinematics were assessed using an 8 camera BTS Smart 7000DX motion analysis system and the Microsoft Kinect® camera system. The agreement and consistency between both uncorrected and correct Kinect kinematic variables and the BTS camera system were assessed using interclass correlations coefficients. Peak sagittal plane kinematics measured using the Microsoft Kinect® camera system explained a significant amount of variance [Range(hip) = 43.5-62.8%; Range(knee) = 67.5-89.6%] in peak kinematics measured using the BTS camera system. Across tasks, peak knee flexion angle and peak hip flexion were found to be consistent and in agreement when the Microsoft Kinect® camera system was directly compared to the BTS camera system but these values were improved following application of a corrective factor. The Microsoft Kinect® may not be an appropriate surrogate for traditional motion analysis technology, but it may have potential applications as a real-time feedback tool in pathological or high injury risk populations.

Validity of a New 3-D Motion Analysis Tool for the Assessment of Knee, Hip and Spine Joint Angles during the Single Leg Squat

“…However, these studies assess movement patterns rather than specific joint angles, and use visual observation as reference standard rather than conventional 3D motion analysis [ 47 , 48 ]. Similar to this study, other markerless 3D MoCap tools such as the Kinect V2, have demonstrated stronger validity for sagittal plane kinematics than for the frontal plane during the single leg squat [ 45 , 49 ]. The difference in accuracy of sagittal plane versus frontal and transverse plane measurements can be explained from a biomechanical point of view.…”

“…This study shows that easily accessible technology is likely to enter the market for a broad audience of professionals from different fields. The recent research interest from orthopedic and neurologic rehabilitation specialists in this type of technology shows that there is a loud call for quantification of many parameters in their specific patient populations [ 2 , 4 , 9 , 17 , 19 , 20 , 21 , 31 , 34 , 45 ]. Every movement related health problem would thus likely have its own clinical relevant movement parameters.…”

Experimental Validation of Depth Cameras for the Parameterization of Functional Balance of Patients in Clinical Tests

“…In recent years, depth cameras have been integrated into rehabilitation protocols in patients with different diseases, such as stroke survivors [13,21,22,23], Parkinson’s disease [24], and cerebral palsy [25], and in different movements such as jumping [26], walking [21,27,28], running [27] or even for transferring a person to a wheelchair [29]. Among the most similar works to our proposal, the paper series from Clark et al [30,31] also presents the Kinect camera as a potential instrument for the assessment of standing balance and postural control.…”

An Automated Method to Extract Three-Dimensional Position Data Using an Infrared Time-of-Flight Camera

“…Both the Xbox 360 and Xbox One Kinect provide a software development kit (SDK) for automated 3D human-pose estimation [4]. Automatic human-pose estimation using Microsoft's SDK has been assessed in many sport and health applications, including functional movement assessment [5] and gait analysis [6]. Whilst automatic human-pose estimation is an extremely useful tool for movement-based analyses, measurement agreement has limited its use as a surrogate motion capture system [5].…”

“…Automatic human-pose estimation using Microsoft's SDK has been assessed in many sport and health applications, including functional movement assessment [5] and gait analysis [6]. Whilst automatic human-pose estimation is an extremely useful tool for movement-based analyses, measurement agreement has limited its use as a surrogate motion capture system [5]. Moreover, whilst joint position estimates contain error [4], the model-based nature of estimation can exacerbate errors for persons deviating from this model (i.e., stature, shape, etc.).…”