Motion analysis method

摘要

The present invention relates to an automated system of measuring and assessing an individual's improvement in motion (for example, a patient's recovery) through exercise performance. In an embodiment of the system of the present invention, two approaches for monitoring movement are introduced for quantifying an individual's performance. Both approaches consider the control population as their reference and consider the difference, or what is referred to in this application as the distance, between the individual's data and the control population as the measure of performance.

主权项

1. A method for analysing an individual's motion through a computer programmed to process information, comprising the steps of:
measuring control linear acceleration and angular velocity, using sensors on at least one control person performing a set of repetitions of an exercise or movement; measuring individual linear acceleration and angular velocity, using sensors on said individual performing a set of repetitions of an exercise or movement; inputting the measured control linear acceleration and angular velocity and individual linear acceleration and angular velocity into said computer to convert to joint angle positions, velocities and accelerations data for said individual and for said at least one control person; segmenting said data such that each segment begins with a start of an exercise or movement repetition and ends when the repetition is finished; extracting feature vectors from said data such that:
a. a control feature vector is V′H=VH(topfeatures) and an individual's feature vector is V′p=Vp(topfeatures) and said top features are a subset of features calculated based on said data that differentiate the individual from the at least one control person, andb. when a progression of data is available, identify and select informative features which are indicative of that progression to be used in said feature vectors and disregard uninformative features which are not indicative of that progression; calculating a mean of the at least one control person's feature vector such that μH=mean(V′H); calculating a diagonal matrix of standard deviations for the at least one control person's feature vector, such that ΣH=diag(std(V′H)); and calculating a distance between one repetition of the exercise or movement performed by said individual and the at least one control person's performance using δi=(V′Pi−μH)TΣh(V′Pi−μH).