US 12,148,317 B2
Systems and methods for monitoring and evaluating body movement
Jeremie Leroyer, Brooklyn, NY (US); and Cyril Porteret, Paris (FR)
Assigned to Prove Labs Inc., Brooklyn, NY (US)
Filed by Prove Labs, Inc., Brooklyn, NY (US)
Filed on Feb. 17, 2023, as Appl. No. 18/170,572.
Application 18/170,572 is a continuation of application No. 18/053,649, filed on Nov. 8, 2022, granted, now 11,776,421.
Application 18/053,649 is a continuation of application No. 16/420,329, filed on May 23, 2019, granted, now 11,521,326, issued on Dec. 6, 2022.
Claims priority of provisional application 62/675,268, filed on May 23, 2018.
Prior Publication US 2023/0206782 A1, Jun. 29, 2023
Int. Cl. G06T 17/05 (2011.01); G06F 21/32 (2013.01); G06T 7/00 (2017.01); G06T 7/246 (2017.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 40/20 (2022.01); G09B 19/00 (2006.01); G06N 3/08 (2023.01); G06V 40/16 (2022.01)
CPC G09B 19/0038 (2013.01) [G06F 21/32 (2013.01); G06T 7/251 (2017.01); G06T 7/97 (2017.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 40/20 (2022.01); G06N 3/08 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/30196 (2013.01); G06V 40/172 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computing device configured to provide recommendations to users based on captured poses, comprising:
one or more processors;
one or more hardware-based memory devices storing computing-readable instructions which, when executed by the one or more processors, cause the computing device to:
receive one or more images of a user's body while the user performs physical movement;
input the captured one or more images into an initial convolutional neural network (CNN) image classification model to infer physical body information;
output, from the initial CNN, at least the inferred physical body information;
input, into a subsequent CNN that is a separate CNN from the initial CNN, at least the output inferred body information derived from the initial CNN, in which the subsequent CNN refines the inferred body information into refined body information;
generate, using the refined body information, a recommendation that suggests a body movement or positioning alteration to the user for their physical movement; and
output the generated recommendation.