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:
Apr. 21, 2025

Filed:

Aug. 03, 2022
Applicants:

Dalong LI, Troy, MI (US);

Rohit S Paranjpe, Rochester Hills, MI (US);

Benjamin J Chappell, Hummelstown, PA (US);

Inventors:

Dalong Li, Troy, MI (US);

Rohit S Paranjpe, Rochester Hills, MI (US);

Benjamin J Chappell, Hummelstown, PA (US);

Assignee:

FCA US LLC, Auburn Hills, MI (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 20/58 (2021.12); G01S 17/894 (2019.12); G01S 17/931 (2019.12); G06V 10/75 (2021.12); G06V 10/778 (2021.12); G06V 10/82 (2021.12); G06V 20/64 (2021.12);
U.S. Cl.
CPC ...
G06V 20/58 (2021.12); G01S 17/894 (2019.12); G01S 17/931 (2019.12); G06V 10/751 (2021.12); G06V 10/778 (2021.12); G06V 10/82 (2021.12); G06V 20/647 (2021.12);
Abstract

Vehicle perception techniques include applying a 3D DNN to a set of inputs to generate 3D detection results including a set of 3D objects, transforming the set of 3D objects onto a set of images as a first set of 2D bounding boxes, applying a 2D DNN to the set of images to generate 2D detection results including a second set of 2D bounding boxes, calculating mean average precision (mAP) values based on a comparison between the first and second sets of 2D bounding boxes, identifying a set or corner cases based on the calculated mAP values, and re-training or updating the 3D DNN using the identified set of corner cases, wherein a performance of the 3D DNN is thereby increased without the use of expensive additional manually and/or automatically annotated training datasets.


Find Patent Forward Citations

Loading…