Method and apparatus for gait analysis

Abstract

A computerized method performed by a processor, and computer program product the method comprising: receiving sensory data of motion by a human subject, the sensory data obtained during motion in an uncontrolled environment; extracting features from the sensory data; identifying a plurality of strides from the features extracted from the sensory data; calculating kinematic parameters of each stride from the plurality of strides from the sensory data; classifying each stride from the plurality of strides in accordance with the kinematic parameters to obtain a stride type; and outputting the stride type for the plurality of strides.

What is claimed is: 
     
         1 . A computerized method performed by a processor, comprising:
 receiving sensory data of motion by a human subject, wherein the sensory data is obtained during motion in an uncontrolled environment, and wherein the motion comprises a sequence of strides of a plurality of stride types;   extracting features from the sensory data;   identifying a plurality of strides from the features extracted from the sensory data;   calculating kinematic parameters of each stride from the plurality of strides from the sensory data;   classifying each stride from the plurality of strides in accordance with the kinematic parameters to obtain for the stride a stride type selected from the plurality of stride types; and   outputting the stride type for the plurality of strides.   
     
     
         2 . The method of  claim 1 , further comprising:
 providing the kinematic parameters to a model associating kinematic parameters and kinetic parameters for the type of gait, for obtaining kinetic forces applied on and by the human subject in response to performing gaits having the kinematic parameters; and   outputting the kinetic parameters.   
     
     
         3 . The method of  claim 2 , further comprising combining the model with a second analytic model, for interpolating kinematic gait properties as a function of foot velocity. 
     
     
         4 . The method of  claim 2 , further comprising:
 combining kinetic parameters of multiple segments to obtain advanced kinetic parameters for a plurality of strides; and   outputting the advanced kinetic parameters.   
     
     
         5 . The method of  claim 1 , wherein at least one feature from the features is selected from the group consisting of: human subject information including: subject height, weight, age, gender, leg length, foot length, or dominant leg; stride information for each stride in a sequence of one or more strides including: side, stride length, stride duration, contact time with the ground, flight ratio, stride change in heading angle, pronation, maximal foot height, or change in height; and ball touch data, including: type or release velocity. 
     
     
         6 . The method of  claim 1 , wherein at least one feature from the features relates to the sensory data in at least one dimension in time or frequency domain. 
     
     
         7 . The method of  claim 1 , wherein at least one feature from the features relates to a three dimensional motion profile of the human subject. 
     
     
         8 . The method of  claim 1 , wherein the sensory data is obtained from at least one sensor mounted on at least one shoe of the human subject. 
     
     
         9 . The method of  claim 1 , wherein the sensory data is obtained from sensors mounted on at least one shoe of the subject and an additional sensor mounted on another location on the human subject. 
     
     
         10 . The method of  claim 1 , wherein the sensory data is obtained from at least one sensor comprising at least one Inertial Measurement Unit (IMU) or a motion capture system. 
     
     
         11 . The method of  claim 1 , wherein the method is used for assessing a medical condition of the human subject. 
     
     
         12 . The method of  claim 1 , further comprising providing an indication to an increased risk of fall or another neurological condition of the human subject based on changes in kinetic and kinematic parameters or recognition of abnormal gait patterns. 
     
     
         13 . A computer program product comprising a computer readable storage medium retaining program instructions, which program instructions when read by a processor, cause the processor to perform a method comprising:
 receiving sensory data of motion by a human subject, wherein the sensory data obtained during motion in an uncontrolled environment, and wherein the motion comprises a sequence of strides of a plurality of stride types;   extracting features from the sensory data;   identifying a plurality of strides from the features extracted from the sensory data;   calculating kinematic parameters of each stride from the plurality of strides from the sensory data;   classifying each stride from the plurality of strides in accordance with the kinematic parameters to obtain for the stride a stride type selected from the plurality of stride types; and   outputting the stride type for the plurality of strides.   
     
     
         14 . The computer program product of  claim 13 , wherein the processor is further adapted to perform:
 providing the kinematic parameters to a second model associating kinematic parameters and kinetic parameters for the type of gait, for obtaining kinetic forces applied on and by the human subject in response to performing gaits having the kinematic parameters; and   outputting the kinetic parameters.