US 11,868,687 B2
Predictive information for free space gesture control and communication
David S. Holz, San Francisco, CA (US); Kevin Horowitz, San Francisco, CA (US); Raffi Bedikian, San Francisco, CA (US); and Hua Yang, Millbrae, CA (US)
Assigned to Ultrahaptics IP Two Limited, Bristol (GB)
Filed by Ultrahaptics IP Two Limited, Bristol (GB)
Filed on Jan. 30, 2023, as Appl. No. 18/161,811.
Application 18/161,811 is a continuation of application No. 17/308,903, filed on May 5, 2021, granted, now 11,568,105.
Application 17/308,903 is a continuation of application No. 16/695,136, filed on Nov. 25, 2019, granted, now 11,010,512, issued on May 18, 2021.
Application 16/695,136 is a continuation of application No. 16/004,119, filed on Jun. 8, 2018, granted, now 10,489,531, issued on Nov. 26, 2019.
Application 16/004,119 is a continuation of application No. 14/530,690, filed on Oct. 31, 2014, granted, now 9,996,638, issued on Jun. 12, 2018.
Claims priority of provisional application 61/898,462, filed on Oct. 31, 2013.
Prior Publication US 2023/0169236 A1, Jun. 1, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 17/00 (2019.01); G06F 30/20 (2020.01); G06F 3/01 (2006.01); G06V 20/64 (2022.01); G06V 40/20 (2022.01)
CPC G06F 30/20 (2020.01) [G06F 3/017 (2013.01); G06V 20/64 (2022.01); G06V 40/28 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method of updating a predictive model using clustering observed points, the method including:
receiving observation information capturing a set of points in a three-dimensional (3D) sensory space;
accessing a predictive model of a hand;
obtaining using points in the set of points and the predictive model, a refined predictive model having refined positions of segments determined for the set of points captured; and
using the predictive model as refined to interpret a control objects's position and/or motion.