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:
Dec. 03, 2019

Filed:

Aug. 29, 2017
Applicant:

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

Inventors:

Iain Melvin, Hopewell, NJ (US);

Eric Cosatto, Red Bank, NJ (US);

Igor Durdanovic, Lawrenceville, NJ (US);

Hans Peter Graf, Lincroft, NJ (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G01S 13/93 (2006.01); G06N 3/08 (2006.01); G06K 9/46 (2006.01); G01S 17/93 (2006.01); B60Q 9/00 (2006.01); G01S 7/20 (2006.01); G01S 7/295 (2006.01); G01S 7/41 (2006.01); G01S 13/86 (2006.01); B60R 1/00 (2006.01); B60W 30/09 (2012.01); G06K 9/00 (2006.01); G06K 9/62 (2006.01);
U.S. Cl.
CPC ...
G01S 13/931 (2013.01); B60Q 9/008 (2013.01); B60R 1/00 (2013.01); B60W 30/09 (2013.01); G01S 7/20 (2013.01); G01S 7/2955 (2013.01); G01S 7/417 (2013.01); G01S 13/867 (2013.01); G01S 17/936 (2013.01); G06K 9/00805 (2013.01); G06K 9/46 (2013.01); G06K 9/6215 (2013.01); G06K 9/6232 (2013.01); G06N 3/08 (2013.01); B60G 2400/823 (2013.01); B60R 2300/301 (2013.01); B60R 2300/8093 (2013.01); B60W 2420/42 (2013.01); B60W 2420/52 (2013.01); G01S 2013/936 (2013.01); G01S 2013/9367 (2013.01); G01S 2013/9375 (2013.01);
Abstract

A computer-implemented method and system are provided. The system includes an image capture device configured to capture image data relative to an ambient environment of a user. The system further includes a processor configured to detect and localize objects, in a real-world map space, from the image data using a trainable object localization Convolutional Neural Network (CNN). The CNN is trained to detect and localize the objects from image and radar pairs that include the image data and radar data for different scenes of a natural environment. The processor is further configured to perform a user-perceptible action responsive to a detection and a localization of an object in an intended path of the user.


Find Patent Forward Citations

Loading…