Understanding the developmental levels of fundamental movement skills has a critical role in the improvement of motor competence in childhood. In this respect, the use of Microsoft Kinect to assess vertical jumping skill and to predict developmental levels in 9- to 12-yr.-old children was evaluated. 41 boys and girls repeated the countermovement jump test three times.
Vertical jumping skill levels were categorized using observational records, while kinematic and temporal parameters were estimated using a biomechanical model based on data acquired by the Kinect. Multivariate analysis of variance (MANOVA) and discriminant analysis verified that the height of the jump and the flight height predict the primary differences in jumping skill developmental levels, and the Kinect-based assessment discriminates these levels.
Markerless motion capture may have the potential to make motion capture technology widely clinically practical. However, the ability of a single markerless camera system to quantify clinically relevant, lower extremity joint angles has not been studied in vivo.
Therefore, the goal of this study was to compare in vivo joint angles calculated using a marker-based motion capture system and a Microsoft Kinect during a squat. Fifteen individuals participated in the study: 8 male, 7 female, height 1.702±0.089m, mass 67.9±10.4kg, age 24±4 years, BMI 23.4±2.2kg/m(2). Marker trajectories and Kinect depth map data of the leg were collected while each subject performed a slow squat motion. Custom code was used to export virtual marker trajectories for the Kinect data.
Each set of marker trajectories was utilized to calculate Cardan knee and hip angles. The patterns of motion were similar between systems with average absolute differences of <5 deg. Peak joint angles showed high between-trial reliability with ICC>0.9 for both systems.
The peak angles calculated by the marker-based and Kinect systems were largely correlated (r>0.55). These results suggest the data from the Kinect can be post processed in way that it may be a feasible markerless motion capture system that can be used in the clinic.
Microsoft's Kinect for Xbox 360 virtual reality (VR) video games are promising rehabilitation options because they involve motivating, full-body movement practice. However, these games were designed for recreational use, which creates challenges for clinical implementation.
Busy clinicians require decision-making support to inform game selection and implementation that address individual therapeutic goals. This article describes the development and preliminary evaluation of a knowledge translation (KT) resource to support clinical decision making about selection and use of Kinect games in physical therapy. The knowledge-to-action framework guided the development of the Kinecting With Clinicians (KWiC) resource. Five physical therapists with VR and video game expertise analyzed the Kinect Adventure games. A consensus-building method was used to arrive at categories to organize clinically relevant attributes guiding game selection and game play.
The process and results of an exploratory usability evaluation of the KWiC resource by clinicians through interviews and focus groups at 4 clinical sites is described. Subsequent steps in the evaluation and KT process are proposed, including making the KWiC resource Web-based and evaluating the utility of the online resource in clinical practice.
The Microsoft Kinect V2 for Windows, also known as the Xbox One Kinect, includes new and potentially far improved depth and image sensors which may increase its accuracy for assessing postural control and balance. The aim of this study was to assess the concurrent validity and reliability of kinematic data recorded using a marker-based three dimensional motion analysis (3DMA) system and the Kinect V2 during a variety of static and dynamic balance assessments.
Thirty healthy adults performed two sessions, separated by one week, consisting of static standing balance tests under different visual (eyes open vs. closed) and supportive (single limb vs. double limb) conditions, and dynamic balance tests consisting of forward and lateral reach and an assessment of limits of stability. Marker coordinate and joint angle data were concurrently recorded using the Kinect V2 skeletal tracking algorithm and the 3DMA system. Task-specific outcome measures from each system on Day 1 and 2 were compared. Concurrent validity of trunk angle data during the dynamic tasks and anterior-posterior range and path length in the static balance tasks was excellent (Pearson's r>0.75). In contrast, concurrent validity for medial-lateral range and path length was poor to modest for all trials except single leg eyes closed balance.
Within device test-retest reliability was variable; however, the results were generally comparable between devices. In conclusion, the Kinect V2 has the potential to be used as a reliable and valid tool for the assessment of some aspects of balance performance.
Treadmill walking is commonly used to analyze several gait cycles in a limited space. Depth cameras, such as the low-cost and easy-to-use Kinect sensor, look promising for gait analysis on a treadmill for routine outpatient clinics.
However, gait analysis is based on accurately detecting gait events (such as heel-strike) by tracking the feet which may be incorrectly recognized with Kinect. Indeed depth images could lead to confusion between the ground and the feet around the contact phase. To tackle this problem we assume that ...
Normalisation of gait data is routine practice to reduce inter-subject variability. Although non-dimensional (N-D) normalisation of data is thought as the most appropriate technique to normalise gait data there have been very few attempts to test this assumption.
This paper describes an investigation that has been completed to assess the effectiveness of N-D normalisation technique.
To explore the outcomes of an Xbox Kinect intervention on balance ability, enjoyment and compliance for previously injured young competitive male athletes.
Experimental pre-/post-test design with random assignment.
Sixty-three previously injured young competitive male athletes, aged 16 ± 1 years.
Participants were divided into three groups: one group received Xbox Kinect (XbK) training, one group received Traditional physiotherapy (TP) training, and one group did not receive any balance training (Control). Intervention involved a 24 min session, twice weekly for 10 weeks.
MAIN OUTCOME MEASURES:
Overall stability index (OSI) and limits of stability (LOS) scores using the Biodex Stability System. Enjoyment using the Physical Activity Enjoyment Scale. Self-reported compliance.
Both experimental groups demonstrated an improvement in OSI and LOS mean scores for the right and the left limb after the intervention. In addition, the results revealed important differences between the experimental groups and the control group on balance test indices. Group enjoyment rating was greater for XbK compared with TP, while the compliance rating was not.
These findings suggest that the use of XbK intervention is a valuable, feasible and pleasant approach in order to improve balance ability of previously injured young competitive male athletes.
Exergames provide a challenging opportunity for home-based training and evaluation of postural control in the elderly population, but affordable sensor technology and algorithms for assessment of whole body movement patterns in the home environment are yet to be developed. The aim of the present study was to evaluate the use of Kinect, a commonly available video game sensor, for capturing and analyzing whole body movement patterns. Healthy adults (n=20) played a weight shifting exergame under five different conditions with varying amplitudes and speed of sway movement, while 3D positions of ten body segments were recorded in the frontal plane using Kinect and a Vicon 3D camera system.
Principal Component Analysis (PCA) was used to extract and compare movement patterns and the variance in individual body segment positions explained by these patterns. Using the identified patterns, balance outcome measures based on spatiotemporal sway characteristics were computed. The results showed that both Vicon and Kinect capture >90% variance of all body segment movements within three PCs.
Kinect-derived movement patterns were found to explain variance in trunk movements accurately, yet explained variance in hand and foot segments was underestimated and overestimated respectively by as much as 30%. Differences between both systems with respect to balance outcome measures range 0.3-64.3%. The results imply that Kinect provides the unique possibility of quantifying balance ability while performing complex tasks in an exergame environment.