US 12,109,016 B2
Method and system for gait analysis
Thomas Ertelt, Berlin (DE)
Assigned to MCG motion capture GmbH, Heidelberg (DE)
Appl. No. 17/255,904
Filed by MCG MOTION CAPTURE GMBH, Heidelberg (DE)
PCT Filed Jun. 28, 2019, PCT No. PCT/EP2019/067401
§ 371(c)(1), (2) Date Dec. 23, 2020,
PCT Pub. No. WO2020/002635, PCT Pub. Date Jan. 2, 2020.
Claims priority of application No. 18180924 (EP), filed on Jun. 29, 2018.
Prior Publication US 2021/0186377 A1, Jun. 24, 2021
Int. Cl. A61B 5/11 (2006.01); A61B 5/103 (2006.01); A61B 5/00 (2006.01)
CPC A61B 5/112 (2013.01) [A61B 5/1038 (2013.01); A61B 5/7267 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method for gait analysis, comprising:
obtaining data including a ground reaction force curve from a force measuring device,
determining a first approximation of the ground reaction force curve by at least a first approximation function defined by a set of coefficients, and
determining a second approximation of the ground reaction force curve by a second approximation function formed on the basis of the set of coefficients of the at least one first approximation function,
wherein the at least one set of coefficients is combined into a coefficient pool from which individual coefficients can be combined to form the second approximation function;
providing a neural network arranged to obtain the at least one set of coefficients as an input variable and to generate a class information as an output variable;
wherein the at least one set of coefficients comprises a maximum value, a position, and a width of the first approximation function;
wherein the output variable is one of the following: a respective sport, in a medical setting a respective pathology or stage of impairment.