US 11,704,907 B2
Depth-based object re-identification
Nikolaos Karianakis, Redmond, WA (US); Zicheng Liu, Bellevue, WA (US); and Yinpeng Chen, Sammamish, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Dec. 17, 2021, as Appl. No. 17/644,899.
Application 17/644,899 is a continuation of application No. 16/688,956, filed on Nov. 19, 2019, granted, now 11,238,300.
Claims priority of provisional application 62/898,501, filed on Sep. 10, 2019.
Prior Publication US 2022/0172450 A1, Jun. 2, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/40 (2022.01); G06N 3/08 (2023.01); G06N 3/006 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/44 (2022.01); G06V 20/52 (2022.01); G06V 40/10 (2022.01)
CPC G06V 20/41 (2022.01) [G06N 3/006 (2013.01); G06N 3/08 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/52 (2022.01); G06V 40/103 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
for a frame of a plurality of frames of a video, assessing a quality of the frame based at least on image noise of the frame;
determining a frame-level confidence that a previously-recognized object is present in the frame;
weighting the determined frame-level confidence based on the assessed quality of the frame; and
assessing an overall confidence that the previously-recognized object is present in the video based at least on the weighted determined frame-level confidence.