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:
Mar. 14, 2023

Filed:

Jun. 23, 2021
Applicant:

Nvidia Corporation, Santa Clara, CA (US);

Inventors:

Nikolai Smolyanskiy, Seattle, WA (US);

Alexey Kamenev, Bellevue, WA (US);

Stan Birchfield, Sammamish, WA (US);

Assignee:

NVIDIA Corporation, Santa Clara, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G01S 17/88 (2006.01); G01S 17/894 (2020.01); G06N 3/02 (2006.01); G06N 3/084 (2023.01); G06T 7/50 (2017.01); G06T 7/80 (2017.01); G06N 3/04 (2023.01); G06T 7/593 (2017.01); G06N 3/088 (2023.01); G06T 1/20 (2006.01); G06K 9/62 (2022.01); G06N 3/063 (2023.01); G01S 17/86 (2020.01); G01S 17/89 (2020.01);
U.S. Cl.
CPC ...
G06N 3/0454 (2013.01); G01S 17/86 (2020.01); G01S 17/89 (2013.01); G06K 9/6215 (2013.01); G06N 3/0481 (2013.01); G06N 3/063 (2013.01); G06N 3/084 (2013.01); G06N 3/088 (2013.01); G06T 1/20 (2013.01); G06T 7/593 (2017.01); G06T 2207/10012 (2013.01); G06T 2207/10052 (2013.01); G06T 2207/20084 (2013.01);
Abstract

Various examples of the present disclosure include a stereoscopic deep neural network (DNN) that produces accurate and reliable results in real-time. Both LIDAR data (supervised training) and photometric error (unsupervised training) may be used to train the DNN in a semi-supervised manner. The stereoscopic DNN may use an exponential linear unit (ELU) activation function to increase processing speeds, as well as a machine learned argmax function that may include a plurality of convolutional layers having trainable parameters to account for context. The stereoscopic DNN may further include layers having an encoder/decoder architecture, where the encoder portion of the layers may include a combination of three-dimensional convolutional layers followed by two-dimensional convolutional layers.


Find Patent Forward Citations

Loading…