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:
Nov. 12, 2019

Filed:

Jul. 03, 2017
Applicant:

Baidu Usa Llc, Sunnyvale, CA (US);

Inventors:

Yu Huang, Sunnyvale, CA (US);

Hsien-Ting Cheng, Sunnyvale, CA (US);

Jun Zhu, Sunnyvale, CA (US);

Weide Zhang, Sunnyvale, CA (US);

Assignee:

BAIDU USA LLC, Sunnyvale, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2006.01); G05D 1/02 (2006.01); G06T 3/40 (2006.01); G06T 7/55 (2017.01); G06K 9/62 (2006.01); H04N 5/232 (2006.01); G06T 11/60 (2006.01); G05D 1/00 (2006.01); G01S 17/89 (2006.01); G01S 17/02 (2006.01); G01S 17/93 (2006.01); G01S 7/48 (2006.01); G06K 9/28 (2006.01); G06K 9/46 (2006.01); H04N 5/225 (2006.01);
U.S. Cl.
CPC ...
G05D 1/0248 (2013.01); G01S 7/4808 (2013.01); G01S 17/023 (2013.01); G01S 17/89 (2013.01); G01S 17/936 (2013.01); G05D 1/0088 (2013.01); G06K 9/00791 (2013.01); G06K 9/28 (2013.01); G06K 9/4628 (2013.01); G06K 9/6269 (2013.01); G06K 9/6289 (2013.01); G06T 3/40 (2013.01); G06T 7/55 (2017.01); G06T 11/60 (2013.01); H04N 5/2258 (2013.01); H04N 5/23238 (2013.01); G06K 9/00201 (2013.01); G06T 2207/10028 (2013.01);
Abstract

In one embodiment, a method or system generates a high resolution 3-D point cloud to operate an autonomous driving vehicle (ADV) from a low resolution 3-D point cloud and camera-captured image(s). The system receives a first image captured by a camera for a driving environment. The system receives a second image representing a first depth map of a first point cloud corresponding to the driving environment. The system upsamples the second image by a predetermined scale factor to match an image scale of the first image. The system generates a second depth map by applying a convolutional neural network (CNN) model to the first image and the upsampled second image, the second depth map having a higher resolution than the first depth map such that the second depth map represents a second point cloud perceiving the driving environment surrounding the ADV.


Find Patent Forward Citations

Loading…