US 12,244,918 B2
Adaptive multi-scale face and body detector
Hamidreza Vaezi Joze, Redmond, WA (US); and Zehua Wei, Seattle, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on May 19, 2023, as Appl. No. 18/199,826.
Application 18/199,826 is a continuation of application No. 17/512,780, filed on Oct. 28, 2021, granted, now 11,700,445.
Prior Publication US 2023/0291993 A1, Sep. 14, 2023
Int. Cl. H04N 23/611 (2023.01); G06F 18/21 (2023.01); G06V 10/32 (2022.01); H04N 23/69 (2023.01); H04N 23/695 (2023.01)
CPC H04N 23/611 (2023.01) [G06F 18/2163 (2023.01); G06V 10/32 (2022.01); H04N 23/69 (2023.01); H04N 23/695 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
obtaining an image;
determining a first object in the image using a first machine learning model, wherein the first machine learning model is trained to detect the first object and generate a level of confidence of detecting the first object as at least a part of a body in the image;
determining, based on a first level of confidence of detecting a second object in the image using the first machine learning model, a region within the image, wherein the region includes the second object, and the first object and the second object are distinct and without overlapping;
determining, based on a second level of confidence associated with detecting the second object as at least a part of another body in the region using a second machine learning model, the second object in the region; and
automatically updating, based on the second object, a zoom setting of a camera to zoom and follow the second object.