US 12,412,419 B2
Tracking unique face identities in videos
Ali Aminian, Piedmont, CA (US); Aashish Kumar Misraa, Santa Clara, CA (US); Kshitiz Garg, Santa Clara, CA (US); and Aseem Agarwala, Seattle, WA (US)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Nov. 7, 2022, as Appl. No. 17/981,985.
Prior Publication US 2024/0153303 A1, May 9, 2024
Int. Cl. G06V 40/16 (2022.01); G06T 7/20 (2017.01); G06V 10/30 (2022.01); G06V 10/762 (2022.01); G06V 20/40 (2022.01)
CPC G06V 40/161 (2022.01) [G06T 7/20 (2013.01); G06V 10/30 (2022.01); G06V 10/762 (2022.01); G06V 20/49 (2022.01); G06V 40/171 (2022.01); G06T 2207/30201 (2013.01); G06V 2201/07 (2022.01)] 20 Claims
OG exemplary drawing
 
1. One or more computer storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform operations, the operations comprising:
generating a plurality of tracklets from a video by performing object tracking on detected faces in frames of the video using locations of detected faces in frames to identity movement of each person's face across consecutive frames in the video, each tracklet comprising a sequence of consecutive frames in which each frame includes a detected face for a person;
clustering the tracklets using a representative face feature vector for detected faces of each tracklet to generate a plurality of clusters; and
storing, in an identity datastore, information comprising a first identifier for a first identity in association with an indication of frames from tracklets in a first cluster from the plurality of clusters.