US 12,443,267 B2
Silhouette-based limb finder determination
Jonathan R. Hoof, Bellevue, WA (US); and Daniel G. Kennett, Bellevue, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jan. 27, 2021, as Appl. No. 17/159,761.
Application 17/159,761 is a continuation of application No. 14/518,089, filed on Oct. 20, 2014, granted, now 10,921,877.
Prior Publication US 2021/0149478 A1, May 20, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/01 (2006.01); A63F 13/213 (2014.01); A63F 13/25 (2014.01); A63F 13/428 (2014.01); G06T 7/13 (2017.01)
CPC G06F 3/011 (2013.01) [A63F 13/213 (2014.09); A63F 13/25 (2014.09); A63F 13/428 (2014.09); G06T 7/13 (2017.01); G06T 2207/20041 (2013.01); G06T 2207/20044 (2013.01); G06T 2207/30172 (2013.01); G06T 2207/30196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
detecting a user within a depth image and assigning a first segmentation value to each of a first plurality of pixels that correspond to the user in the depth image, wherein the first plurality of pixels that correspond to the user in the depth image comprise a depth-based silhouette;
detecting an object within the depth image and assigning a second segmentation value to each of a second plurality of pixels that correspond to the object, wherein the second plurality of pixels in the depth image are not associated with the user;
assigning a third segmentation value to a third plurality of pixels in the depth image that are not associated with the user or the object;
generating a path, based at least in part on a first distance field and a second distance field, from an extremity point on the depth-based silhouette to a target location in the depth-based silhouette, wherein the first distance field indicates a first distance from within the depth-based silhouette to a silhouette edge of the depth-based silhouette, and the second distance field indicates a second distance from within the depth-based silhouette to the target location in the depth-based silhouette; and
generating a pixel image representation of the depth-based silhouette depicting the path inside the depth-based silhouette for determining a limb in the depth-based silhouette.