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:
May. 08, 2018

Filed:

Nov. 03, 2016
Applicant:

Nec Laboratories America, Inc., Princeton, NJ (US);

Inventors:

Wongun Choi, Lexington, MA (US);

Yuanqing Lin, Sunnyvale, CA (US);

Yu Xiang, Palo Alto, CA (US);

Silvio Savarese, Stanford, CA (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2006.01); G06N 3/08 (2006.01); G06K 9/32 (2006.01); G06K 9/62 (2006.01); G06T 7/73 (2017.01); G06E 1/00 (2006.01);
U.S. Cl.
CPC ...
G06N 3/08 (2013.01); G06K 9/3233 (2013.01); G06K 9/628 (2013.01); G06T 7/73 (2017.01); G06T 2207/20084 (2013.01); G06T 2207/30261 (2013.01);
Abstract

A computer-implemented method for detecting objects by using subcategory-aware convolutional neural networks (CNNs) is presented. The method includes generating object region proposals from an image by a region proposal network (RPN) which utilizes subcategory information, and classifying and refining the object region proposals by an object detection network (ODN) that simultaneously performs object category classification, subcategory classification, and bounding box regression. The image is an image pyramid used as input to the RPN and the ODN. The RPN and the ODN each include a feature extrapolating layer to detect object categories with scale variations among the objects.


Find Patent Forward Citations

Loading…