US 12,244,967 B2
Pixel-level based micro-feature extraction
Wesley Kenneth Cobb, The Woodlands, TX (US); Rajkiran K. Gottumukkal, Houston, TX (US); Kishor Adinath Saitwal, Houston, TX (US); Ming-Jung Seow, The Woodlands, TX (US); Gang Xu, Katy, TX (US); Lon W. Risinger, Katy, TX (US); and Jeff Graham, League City, TX (US)
Assigned to Intellective Ai, Inc., Dallas, TX (US)
Filed by Intellective Ai, Inc., Dallas, TX (US)
Filed on Sep. 13, 2022, as Appl. No. 17/943,922.
Application 17/943,922 is a division of application No. 16/931,921, filed on Jul. 17, 2020, granted, now 11,468,660.
Application 16/931,921 is a continuation of application No. 16/033,264, filed on Jul. 12, 2018, granted, now 10,755,131, issued on Aug. 25, 2020.
Application 16/033,264 is a continuation of application No. 15/461,139, filed on Mar. 16, 2017, granted, now 10,049,293, issued on Aug. 14, 2018.
Application 15/461,139 is a continuation of application No. 12/543,141, filed on Aug. 18, 2009, granted, now 9,633,275, issued on Apr. 25, 2017.
Claims priority of provisional application 61/096,031, filed on Sep. 11, 2008.
Prior Publication US 2023/0005238 A1, Jan. 5, 2023
Int. Cl. G06K 9/00 (2022.01); G06V 10/25 (2022.01); G06V 10/40 (2022.01); G06V 10/46 (2022.01); G06V 10/50 (2022.01); H04N 7/18 (2006.01)
CPC H04N 7/18 (2013.01) [G06V 10/25 (2022.01); G06V 10/40 (2022.01); G06V 10/46 (2022.01); G06V 10/507 (2022.01); G06V 10/473 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
identifying, via a processor, a plurality of foreground objects depicted in a sequence of video frames;
for each foreground object from the plurality of foreground objects, deriving feature data for that foreground object from each video frame from the sequence of video frames that depicts the foreground object;
generating, via the processor and based on the derived feature data of a first foreground object from the plurality of foreground objects, an object type model;
correlating, via the processor, the derived feature data of a second foreground object from the plurality of foreground objects with the object type model by mapping the derived feature data of the second foreground object to an adaptive resonance theory (ART) network; and
in response to the correlating the derived feature data for the second foreground object with the object type model, assigning an object type identifier to the second foreground object to indicate that the second foreground object is an instance of an object type associated with the object type model.