US 12,260,679 B1
Hand initialization for machine learning based gesture recognition
Jonathan Marsden, San Mateo, CA (US); Raffi Bedikian, San Francisco, CA (US); and David Samuel Holz, San Francisco, CA (US)
Assigned to ULTRAHAPTICS IP TWO LIMITED, Bristol (GB)
Filed by ULTRAHAPTICS IP TWO LIMITED, Bristol (GB)
Filed on Dec. 20, 2023, as Appl. No. 18/391,574.
Application 18/391,574 is a continuation of application No. 15/432,876, filed on Feb. 14, 2017, granted, now 11,854,308.
Claims priority of provisional application 62/335,542, filed on May 12, 2016.
Claims priority of provisional application 62/296,561, filed on Feb. 17, 2016.
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 40/20 (2022.01); G06F 3/01 (2006.01); G06F 18/21 (2023.01); G06F 18/22 (2023.01); G06V 10/44 (2022.01); G06V 30/194 (2022.01); G06V 40/10 (2022.01)
CPC G06V 40/28 (2022.01) [G06F 3/017 (2013.01); G06F 18/217 (2023.01); G06F 18/22 (2023.01); G06V 10/454 (2022.01); G06V 30/194 (2022.01); G06V 40/113 (2022.01)] 21 Claims
OG exemplary drawing
 
1. A method of determining a hand pose using neural network systems, the method including:
receiving a first set of estimates of hand position parameters from one or more generalist neural networks and/or specialist neural networks for at least one hand joint of a plurality of hand joints;
for the at least one hand joint of the plurality of hand joints, determining a principal distribution of the first set of estimates;
receiving a second set of estimates of hand position parameters from the one or more generalist neural networks and/or specialist neural networks for the at least one hand joint of the plurality of hand joints; and
for the at least one hand joint of the plurality of hand joints:
calculating a similarity measure between the second set of estimates and the principal distribution of the first set of estimates;
identifying select estimates in the second set of estimates based on the similarity measure;
calculating contribution weights of the select estimates based on the similarity measure; and
determining a principal distribution of the second set of estimates based on the contribution weights of the select estimates.