US 12,013,986 B2
Method and system for hand pose detection
Ayan Sinha, West Lafayette, IN (US); Chiho Choi, West Lafayette, IN (US); Joon Hee Choi, West Lafayette, IN (US); and Karthik Ramani, West Lafayette, IN (US)
Assigned to Purdue Research Foundation, West Lafayette, IN (US)
Filed by Purdue Research Foundation, West Lafayette, IN (US)
Filed on Jun. 13, 2022, as Appl. No. 17/838,887.
Application 16/436,588 is a division of application No. 15/380,002, filed on Dec. 15, 2016, granted, now 10,318,008, issued on Jun. 11, 2019.
Application 17/838,887 is a continuation of application No. 17/107,160, filed on Nov. 30, 2020, granted, now 11,360,570.
Application 17/107,160 is a continuation of application No. 16/707,936, filed on Dec. 9, 2019, granted, now 10,852,840.
Application 16/707,936 is a continuation of application No. 16/436,588, filed on Jun. 10, 2019, granted, now 10,503,270, issued on Dec. 10, 2019.
Claims priority of provisional application 62/267,634, filed on Dec. 15, 2015.
Prior Publication US 2023/0044664 A1, Feb. 9, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/01 (2006.01); G06N 20/00 (2019.01); G06V 10/44 (2022.01); G06V 20/64 (2022.01); G06V 30/194 (2022.01); G06V 40/10 (2022.01); H04N 13/271 (2018.01)
CPC G06F 3/017 (2013.01) [G06N 20/00 (2019.01); G06V 10/454 (2022.01); G06V 20/653 (2022.01); G06V 30/194 (2022.01); G06V 40/11 (2022.01); G06V 40/113 (2022.01); H04N 13/271 (2018.05)] 20 Claims
OG exemplary drawing
 
1. A system for computer human interaction comprising:
a camera configured to generate data of a hand of a user;
an output device;
a memory storing at least a first neural network; and
a processor operatively connected to the camera, the output device, and the memory, the processor being configured to:
receive map data of the hand of the user from the camera;
generate, using the first neural network, a first plurality of activation features based at least in part on the map data, the first plurality of activation features corresponding to a joint angle of a wrist in the hand;
perform a first search in a predetermined plurality of activation features stored in a database stored in the memory to identify a first plurality of hand pose parameters for the wrist;
generate a hand pose model corresponding to the hand of the user based at least in part on the first plurality of hand pose parameters; and
generate an output with the output device in response to input from the user based at least in part on the hand pose model.