Automated extraction and validation of children's gait parameters with the Kinect.

BACKGROUND: Gait analysis for therapy regimen prescription and monitoring requires patients to physically access clinics with specialized equipment. The timely availability of such infrastructure at the right frequency is especially important for small children. Besides being very costly, this is a challenge for many children living in rural areas. This is why this work develops a low-cost, portable, and automated approach for in-home gait analysis, based on the Microsoft Kinect. METHODS: A robust and efficient method for extracting gait parameters is introduced, which copes with the high variability of noisy Kinect skeleton tracking data experienced across the population of young children. This is achieved by temporally segmenting the data with an approach based on coupling a probabilistic matching of stride template models, learned offline, with the estimation of their global and local temporal scaling. A preliminary study conducted on healthy children between 2 and 4 years of age is performed to analyze the accuracy, precision, repeatability, and concurrent validity of the proposed method against the GAITRite when measuring several spatial and temporal children's gait parameters. RESULTS: The method has excellent accuracy and good precision, with segmenting temporal sequences of body joint locations into stride and step cycles. Also, the spatial and temporal gait parameters, estimated automatically, exhibit good concurrent validity with those provided by the GAITRite, as well as very good repeatability. In particular, on a range of nine gait parameters, the relative and absolute agreements were found to be good and excellent, and the overall agreements were found to be good and moderate. CONCLUSION: This work enables and validates the automated use of the Kinect for children's gait analysis in healthy subjects. In particular, the approach makes a step forward towards developing a low-cost, portable, parent-operated in-home tool for clinicians assisting young children.

Classification of Normal and Pathological Gait in Young Children Based on Foot Pressure Data.

Human gait recognition, an active research topic in computer vision, is generally based on data obtained from images/videos. We applied computer vision technology to classify pathology-related changes in gait in young children using a foot-pressure database collected using the GAITRite walkway system. As foot positioning changes with children's development, we also investigated the possibility of age estimation based on this data. Our results demonstrate that the data collected by the GAITRite system can be used for normal/pathological gait classification. Combining age information and normal/pathological gait classification increases the accuracy of the classifier. This novel approach could support the development of an accurate, real-time, and economic measure of gait abnormalities in children, able to provide important feedback to clinicians regarding the effect of rehabilitation interventions, and to support targeted treatment modifications.

Gait parameters associated with balance in healthy 2- to 4-year-old children.

The use of validated measurements of gait and balance are crucial to establish baseline function and assess effectiveness of therapeutic interventions. Gait in children changes with motor development requiring frequent observations to effectively track progress. Standardized baseline spatiotemporal measurements and a greater understanding of the relationship between gait and balance would provide important feedback to clinicians regarding the effectiveness of rehabilitation and guide treatment modifications. 84 subjects (2.0-4.9 years) walked along the GAITRite(®), a walkway that records spatiotemporal parameters. The Pediatric Balance Scale (PBS) was administered to assess balance. Comparison of spatiotemporal parameter means between age groups showed trends associated with motor development similar to the ones described in the literature such as decreased cadence and increased step/stride length with increasing age. However, no significant differences in normalized spatiotemporal parameters were found between age groups. Age, leg length, cadence, step/stride length, step/stance time, and single/double support time showed significant correlation with balance scores. When the parameters were grouped into spatial, temporal, and age-related components using principal components analysis and included in a multiple regression model, they significantly predicted 51% of the balance score variance. Age-related components most strongly predicted balance outcomes. We suggest that balance can potentially be evaluated by assessment of spatial, temporal, and age-related characteristics of gait such as step length, cadence, and leg length. This suggests the possibility of developing new gait measurement technology that could provide functional assessment and track improvements during rehabilitation regimens. If the same model can be applied to monitor treatment efficacy in children with gait abnormalities remains to be addressed.