The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 05, 2023

Filed:

Nov. 12, 2020
Applicant:

L'oreal, Paris, FR;

Inventors:

Abdalla Ahmed, Toronto, CA;

Irina Kezele, Toronto, CA;

Parham Aarabi, Richmond Hill, CA;

Brendan Duke, Toronto, CA;

Assignee:

L'Oreal, Paris, FR;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 7/11 (2017.01); G06T 7/174 (2017.01); G06T 7/20 (2017.01); G06T 9/00 (2006.01); G06N 3/08 (2023.01); G06V 20/40 (2022.01); G06V 40/12 (2022.01); G06V 10/771 (2022.01); G06V 10/82 (2022.01); G06V 10/26 (2022.01); G06V 40/10 (2022.01); G06V 10/62 (2022.01);
U.S. Cl.
CPC ...
G06T 7/11 (2017.01); G06N 3/08 (2013.01); G06T 7/174 (2017.01); G06T 7/20 (2013.01); G06T 9/002 (2013.01); G06V 10/273 (2022.01); G06V 10/771 (2022.01); G06V 10/82 (2022.01); G06V 20/40 (2022.01); G06V 40/107 (2022.01); G06V 40/12 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20132 (2013.01); G06V 10/62 (2022.01);
Abstract

There are provided methods and computing devices using semi-supervised learning to perform end-to-end video object segmentation, tracking respective object(s) from a single-frame annotation of a reference frame through a video sequence of frames. A known deep learning model may be used to annotate the reference frame to provide ground truth locations and masks for each respective object. A current frame is processed to determine current frame object locations, defining object scoremaps as a normalized cross-correlation between encoded object features of the current frame and encoded object features of a previous frame. Scoremaps for each of more than one previous frame may be defined. An Intersection over Union (IoU) function, responsive to the scoremaps, ranks candidate object proposals defined from the reference frame annotation to associate the respective objects to respective locations in the current frame. Pixel-wise overlap may be removed using a merge function responsive to the scoremaps.


Find Patent Forward Citations

Loading…