US 12,190,640 B2
Personalized fitness activity training using augmented-reality based avatar
Mahima Rao, Bangalore (IN); Teli Pooja, Bangalore (IN); Sankaran Kesavan Namboodiri, Bangalore (IN); and Anubhav Srivastava, Bangalore (IN)
Assigned to SONY GROUP CORPORATION, Tokyo (JP)
Filed by SONY GROUP CORPORATION, Tokyo (JP)
Filed on Aug. 27, 2021, as Appl. No. 17/459,306.
Prior Publication US 2023/0069758 A1, Mar. 2, 2023
Int. Cl. G06V 40/20 (2022.01); A63B 24/00 (2006.01); A63B 71/06 (2006.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06T 7/246 (2017.01); G06T 13/40 (2011.01); G06T 13/80 (2011.01)
CPC G06V 40/23 (2022.01) [A63B 24/0062 (2013.01); A63B 24/0075 (2013.01); A63B 71/0622 (2013.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06T 7/251 (2017.01); G06T 13/40 (2013.01); G06T 13/80 (2013.01); A63B 2024/0068 (2013.01); A63B 2071/063 (2013.01); A63B 2220/24 (2013.01); A63B 2230/62 (2013.01); G06T 2200/24 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01)] 19 Claims
OG exemplary drawing
 
1. An electronic device, comprising:
circuitry configured to:
receive a set of images of a set of users engaged in a first fitness activity, wherein
the set of users comprises a first user and a second user, and
the set of images is captured for a duration in which the set of users are engaged in the first fitness activity;
generate an augmented-reality display that includes a set of avatars and an image of the set of users based on the set of images, wherein the set of avatars comprises a first avatar associated with the first user and a second avatar associated with the second user;
control a display device to render the generated augmented-reality display, wherein the rendered augmented-reality display includes the set of avatars configured to perform the first fitness activity;
determine posture information of each user of the set of users based on the set of images and the first fitness activity;
determine real-time feedback for each user of the set of users based on application of a first neural network model on the determined posture information, wherein the determination of the real-time feedback is further based on performance of the first fitness activity by a respective user of the set of users; and
control one of the first avatar or the second avatar to output the determined real-time feedback in the augmented-reality display.