US 11,887,314 B2
Compressed domain motion detection
Megha Jain, Brooklyn, NY (US); Sayre Blades, Madison, NJ (US); and Jay Ridgeway, Falls Church, VA (US)
Assigned to Smartthings, Inc., Minneapolis, MN (US)
Filed by SmartThings, Inc., Minneapolis, MN (US)
Filed on Nov. 8, 2021, as Appl. No. 17/521,842.
Prior Publication US 2023/0147494 A1, May 11, 2023
Int. Cl. G06V 20/70 (2022.01); G06T 7/223 (2017.01); G06V 20/40 (2022.01); G06V 10/74 (2022.01); G06N 5/01 (2023.01)
CPC G06T 7/223 (2017.01) [G06N 5/01 (2023.01); G06V 10/761 (2022.01); G06V 20/46 (2022.01); G06V 20/48 (2022.01); G06V 20/70 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
receiving compressed video data;
extracting macroblocks and motion vectors for a plurality of frames in the compressed video data;
identifying frame-level features for each of the plurality of frames based on the macroblocks and the motion vectors;
calculating similarity features for each of the identified frame-level features based on the frame-level features identified in consecutive frames;
predicting motion for each of the plurality of frames by providing the frame-level features and the similarity features into a model trained to detect motion; and
predicting event boundaries in the compressed video data by providing the frame-level features into a second model trained to identify event boundaries.