| CPC A63B 24/0006 (2013.01) [A63B 24/0062 (2013.01); G06N 20/00 (2019.01); G06V 20/46 (2022.01); G06V 40/20 (2022.01); A63B 2024/0012 (2013.01); A63B 2024/0065 (2013.01); A63B 2024/0068 (2013.01)] | 20 Claims |
|
1. A computer-implemented method for implementing machine learning to generate a suggestion for improving running gait, comprising:
accessing, by at least one computing device, video data from at least one video frame captured by at least one imaging device;
executing, by the at least one computing device, at least one machine learning routine using the video data to generate positional data of anatomical landmarks of a human or bipedal non-human subject in the at least one video frame;
generating, by the at least one computing device, at least one of a gait metric and a gait characteristic for at least one stage of a gait cycle based at least in part on the positional data;
determining, by the at least one computing device, at least one of an optimal gait cycle for a given body part or gait metric of the subject that may be adjusted for velocity of the subject or at least one demographic or environmental covariable;
determining, by the at least one computing device, a difference and a similarity between the gait cycle of the subject and the optimal gait cycle as a function of gait cycle completion and at each of the at least one stage of the gait cycle of the subject;
generating, by the at least one computing device, a suggested change to movement patterns of the subject at specific timepoints and stages of the gait cycle that minimize the difference between the gait cycle of the subject and the optimal gait cycle; and
causing, by the at least one computing device, the suggested change to the movement patterns to be shown on a display device.
|