US 11,743,588 B1
Object selection in computer vision
Yu Shu, Foster City, CA (US); Yahia Chafik Chehadeh, Palo Alto, CA (US); Heliben Dhrumil Desai, San Jose, CA (US); and Young Sun Kim, Dublin, CA (US)
Assigned to AMAZON TECHNOLOGIES, INC., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Nov. 4, 2020, as Appl. No. 17/89,322.
Claims priority of provisional application 63/081,422, filed on Sep. 22, 2020.
Int. Cl. H04N 23/695 (2023.01); H04N 7/14 (2006.01); G06V 40/10 (2022.01); G10L 15/22 (2006.01)
CPC H04N 23/695 (2023.01) [G06V 40/10 (2022.01); H04N 7/141 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method of selecting an object to track with a camera of a first device, comprising:
detecting a first person and a second person represented in a first frame of image data;
calculating a first weight for the first person by multiplying a first amount of time that the first person has been within a field-of-view of the camera by a start weight value;
calculating a second weight for the second person by multiplying a second amount of time that the second person has been within the field-of-view of the camera by the start weight value;
determining a first priority level for the first person using the first weight and a first threshold for a first property related to detection of objects by the camera;
determining a second priority level for the second person using the second weight and the first threshold; and
controlling the camera, using the first priority level and the second priority level, to track the first person within frames of image data generated by the first device.