US 12,079,990 B2
Leg muscle strength estimation system and leg muscle strength estimation method
Takahiro Aihara, Osaka (JP); Taichi Hamatsuka, Osaka (JP); Yoshihiro Matsumura, Osaka (JP); Takashi Uchida, Hyogo (JP); Kengo Wada, Osaka (JP); Takahiro Hiyama, Tokyo (JP); Akira Matsubara, Osaka (JP); Manabu Yumine, Osaka (JP); and Yoshikuni Sato, Tokyo (JP)
Assigned to PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD., Osaka (JP)
Appl. No. 17/601,655
Filed by Panasonic Intellectual Property Management Co., Ltd., Osaka (JP)
PCT Filed Feb. 7, 2020, PCT No. PCT/JP2020/004704
§ 371(c)(1), (2) Date Oct. 5, 2021,
PCT Pub. No. WO2020/208922, PCT Pub. Date Oct. 15, 2020.
Claims priority of application No. 2019-074422 (JP), filed on Apr. 9, 2019.
Prior Publication US 2022/0198658 A1, Jun. 23, 2022
Int. Cl. G06T 7/00 (2017.01); G06V 40/20 (2022.01)
CPC G06T 7/0012 (2013.01) [G06V 40/25 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30004 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A leg muscle strength estimation system, comprising:
a camera that obtains an image including a user that is walking as a subject of the image; and
a processor and a memory storing a program, wherein:
the program, when executed by the processor, causes the processor to:
identify a two-dimensional skeletal model of the user based on the image obtained;
use a machine learning model to estimate a three-dimensional skeletal model of the user based on the two-dimensional skeletal model identified;
obtain a knee flexion angle of the user while the user is walking based on the three-dimensional skeletal model estimated; and
estimate a leg muscle strength of the user based on the knee flexion angle of the user, and
the smaller the knee flexion angle of the user while the user is walking is, the greater the leg muscle strength of the user is estimated to be.