US 11,694,433 B2
Detection of projected infrared patterns using difference of Gaussian and blob identification
Wen-Sheng Chu, Santa Clara, CA (US); and Kuntal Sengupta, San Jose, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 17/421,505
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Feb. 15, 2019, PCT No. PCT/US2019/018173
§ 371(c)(1), (2) Date Jul. 8, 2021,
PCT Pub. No. WO2020/167314, PCT Pub. Date Aug. 20, 2020.
Prior Publication US 2022/0083775 A1, Mar. 17, 2022
Int. Cl. G06K 9/00 (2022.01); G06V 20/10 (2022.01); G06T 7/521 (2017.01); G06T 7/73 (2017.01); G06V 10/141 (2022.01); G06V 10/94 (2022.01); G06V 10/22 (2022.01); G06F 18/22 (2023.01); H04N 23/56 (2023.01)
CPC G06V 20/10 (2022.01) [G06F 18/22 (2023.01); G06T 7/521 (2017.01); G06T 7/73 (2017.01); G06V 10/141 (2022.01); G06V 10/22 (2022.01); G06V 10/95 (2022.01); H04N 23/56 (2023.01); G06T 2207/10048 (2013.01); G06T 2207/20084 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method of differentiating between dot and flood pattern illumination of an object comprising:
obtaining, by a computing system, an infrared image of the object;
determining, by the computing system, a difference of Gaussian image that represents features of the infrared image that have spatial frequencies within a spatial frequency range defined by a first Gaussian operator and a second Gaussian operator;
identifying, by the computing system, one or more blob regions within the difference of Gaussian image, wherein each blob region of the one or more blob regions comprises a region of connected pixels in the difference of Gaussian image; and
based on identifying the one or more blob regions within the difference of Gaussian image, determining, by the computing system, whether the infrared image represents the object illuminated by a dot pattern or a flood pattern projected onto the object by one or more infrared projectors.