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:
Feb. 25, 2025

Filed:

Jul. 30, 2021
Applicant:

Toyota Research Institute, Inc., Los Altos, CA (US);

Inventors:

Haofeng Chen, Stanford, CA (US);

Arjun Bhargava, San Francisco, CA (US);

Rares Andrei Ambrus, San Francisco, CA (US);

Sudeep Pillai, Santa Clara, CA (US);

Assignee:

TOYOTA RESEARCH INSTITUTE, INC., Los Altos, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 10/46 (2022.01); G06T 3/18 (2024.01); G06T 7/60 (2017.01); G06T 9/00 (2006.01); G06V 20/40 (2022.01); G06V 20/56 (2022.01);
U.S. Cl.
CPC ...
G06V 10/462 (2022.01); G06T 3/18 (2024.01); G06T 7/60 (2013.01); G06T 9/00 (2013.01); G06V 20/46 (2022.01); G06V 20/56 (2022.01); G06T 2207/30236 (2013.01); G06T 2207/30241 (2013.01); G06T 2207/30248 (2013.01);
Abstract

A method for 2D semantic keypoint detection and tracking is described. The method includes learning embedded descriptors of salient object keypoints detected in previous images according to a descriptor embedding space model. The method also includes predicting, using a shared image encoder backbone, salient object keypoints within a current image of a video stream. The method further includes inferring an object represented by the predicted, salient object keypoints within the current image of the video stream. The method also includes tracking the inferred object by matching embedded descriptors of the predicted, salient object keypoints representing the inferred object within the previous images of the video stream based on the descriptor embedding space model.


Find Patent Forward Citations

Loading…