Development of a Kinect Software Tool to Classify Movements during Active Video Gaming

Abstract

While it has been established that using full body motion to play active video games results in increased levels of energy expenditure, there is little information on the classification of human movement during active video game play in relationship to fundamental movement skills. The aim of this study was to validate software utilising Kinect sensor motion capture technology to recognise fundamental movement skills (FMS), during active video game play. Two human assessors rated jumping and side-stepping and these assessments were compared to the Kinect Action Recognition Tool (KART), to establish a level of agreement and determine the number of movements completed during five minutes of active video game play, for 43 children (m = 12 years 7 months ± 1 year 6 months). During five minutes of active video game play, inter-rater reliability, when examining the two human raters, was found to be higher for the jump (r = 0.94, p < .01) than the sidestep (r = 0.87, p < .01), although both were excellent. Excellent reliability was also found between human raters and the KART system for the jump (r = 0.84, p, .01) and moderate reliability for sidestep (r = 0.6983, p < .01) during game play, demonstrating that both humans and KART had higher agreement for jumps than sidesteps in the game play condition. The results of the study provide confidence that the Kinect sensor can be used to count the number of jumps and sidestep during five minutes of active video game play with a similar level of accuracy as human raters. However, in contrast to humans, the KART system required a fraction of the time to analyse and tabulate the results.

Exploring Movement Impairments in Patients With Parkinson's Disease Using the Microsoft Kinect Sensor: A Feasibility Study

“…Initially developed as an entertainment device, e.g., used for dancing games, the Kinect sensor is now in widespread research use, including neuro-rehabilitation (31), assessment of post-stroke movement impairment (32), and classification of movements during active video gaming (33). In our study of 30 patients with PD and 33 healthy controls, we found a highly significant association between prolonged time of motor performance in the Motorgame and higher scores of MDS-UPDRS items related to right hand movements (bradykinesia).…”

Quantifying Physical Activity in Young Children Using a Three-Dimensional Camera

“…Computer vision uses an array of techniques from fields such as engineering and machine learning to extract meaningful information (e.g., facial features and hand gestures) from digital images including video [7]. While a small number of studies have used custom computer vision algorithms to convert video-recorded PA behaviors into quantifiable PA signals [6,[8][9][10][11], no study has validated such a method for estimating PA volumes and intensities in young children from these signals. A recent report pointed toward the potential benefits 2 of 18 of using computer vision, rather than wearable sensors, to measure children's physical activity while indoors at school [12].…”

“…Of the available studies that have used computer vision to specifically estimate PA volumes [6,8,[10][11][12], few have expressly calibrated an algorithm to quantify and classify activity data in children [8]. A study of 10-year-old children appears to be the first to demonstrate the feasibility of using a ceiling-mounted camera to automatically derive estimates of PA velocities in bidimensional space [8].…”

“…While the feasibility and validity of using computer vision to estimate activity volumes and intensities appears promising [6,[8][9][10][11] and the use of such technology for estimating children's PA while indoors has been presented as a logical step forward [12], little is known about the use of computer vision methods to measure PA in young children. Given the lack of validated methods for assessing young children's PA indoors from video data via automated processes, and aiming toward developing more robust contextual models of physical activity behavior, the need for further research on 3D video data calibration for estimating physical activity levels and volumes in young children is clear.…”

Gesture based Human Computer Interaction for Athletic Training

“…In order to bypass the lower extremities inaccuracy a technique that relies on knee joint relative angle has been proposed to detect foot-off and foot contact during the gait cycle [9]. The Kinect was successfully used for the classification of human movement during active video game play in relationship to fundamental movement skill [10].…”