	US 12,192,625 B2
	Direct scale level selection for multilevel feature tracking under motion blur
Matthias Kalkgruber, Vienna (AT); and Daniel Wolf, Mödling (AT)
Assigned to SNAP INC., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on May 22, 2023, as Appl. No. 18/321,565.
Application 18/321,565 is a continuation of application No. 17/521,109, filed on Nov. 8, 2021, granted, now 11,683,585.
Claims priority of provisional application 63/190,101, filed on May 18, 2021.
Prior Publication US 2023/0300464 A1, Sep. 21, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 23/68 (2023.01); G06T 3/40 (2024.01); G06T 5/70 (2024.01); G06T 7/20 (2017.01); G06V 10/44 (2022.01)

CPC H04N 23/6811 (2023.01) [G06T 3/40 (2013.01); G06T 5/70 (2024.01); G06T 7/20 (2013.01); G06V 10/443 (2022.01); H04N 23/6812 (2023.01)]

20 Claims

1. A method comprising:

accessing a first image and a second image following the first image, the first image and the second image generated by an optical sensor of a visual tracking system;

determining a first motion blur level of the first image and a second motion blur level of the second image;

identifying a scale change between the first image and the second image;

calculating a first matching level based on the first motion blur level, and a second matching level based on the second motion blur level;

determining a base matching level based on a maximum of the first matching level and the second matching level; and

adjusting the base matching level based on the scale change.