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:
Feb. 28, 2023

Filed:

Dec. 21, 2020
Applicant:

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

Inventors:

Yi-Hsuan Tsai, Santa Clara, CA (US);

Kihyuk Sohn, Fremont, CA (US);

Buyu Liu, Cupertino, CA (US);

Manmohan Chandraker, Santa Clara, CA (US);

Jong-Chyi Su, Amherst, MA (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2022.01); G06V 20/58 (2022.01); G06K 9/62 (2022.01); B60W 30/095 (2012.01); B60W 30/09 (2012.01); B60W 10/18 (2012.01); B60W 10/20 (2006.01); G08G 1/16 (2006.01); B60W 50/00 (2006.01); G06N 3/08 (2023.01); G06N 3/04 (2023.01);
U.S. Cl.
CPC ...
G06V 20/58 (2022.01); B60W 10/18 (2013.01); B60W 10/20 (2013.01); B60W 30/09 (2013.01); B60W 30/0956 (2013.01); B60W 50/0097 (2013.01); G06K 9/6259 (2013.01); G06K 9/6261 (2013.01); G06N 3/0454 (2013.01); G06N 3/08 (2013.01); G08G 1/166 (2013.01); B60W 2420/42 (2013.01); B60W 2554/4026 (2020.02); B60W 2554/4029 (2020.02); B60W 2555/20 (2020.02);
Abstract

Systems and methods for obstacle detection are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having obstacles. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.


Find Patent Forward Citations

Loading…