US 11,860,038 B2
Method, apparatus and system for passive infrared sensor framework
Yash Modi, San Mateo, CA (US); Mark Rajan Malhotra, San Mateo, CA (US); Gwendolyn van der Linden, Redwood City, CA (US); Dongeek Shin, Mountain View, CA (US); and Michael Dixon, Sunnyvale, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Oct. 7, 2021, as Appl. No. 17/496,266.
Application 17/496,266 is a continuation of application No. 16/894,047, filed on Jun. 5, 2020, granted, now 11,175,185.
Application 16/894,047 is a continuation of application No. 15/430,256, filed on Feb. 10, 2017, granted, now 10,712,204, issued on Jul. 14, 2020.
Prior Publication US 2022/0026277 A1, Jan. 27, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G01J 5/00 (2022.01); G08B 13/193 (2006.01); G08B 13/191 (2006.01); G08B 13/196 (2006.01); G08B 29/18 (2006.01); G06V 20/52 (2022.01); G01J 5/02 (2022.01); G01J 5/10 (2006.01)
CPC G01J 5/0025 (2013.01) [G01J 5/025 (2013.01); G01J 5/10 (2013.01); G06V 20/52 (2022.01); G08B 13/191 (2013.01); G08B 13/193 (2013.01); G08B 13/19602 (2013.01); G08B 29/188 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
detecting, with a passive infrared sensor (PIR), levels of infrared radiation in a field of view (FOV) of the PIR;
generating a signal based on the levels of infrared radiation detected with the PIR, the signal having values used to detect a change in the levels of infrared radiation as detected with the PIR;
extracting a local feature from a sample of the signal by tracking an absolute deviation of the sample of the signal relative to a threshold predetermined to approximate a non-environmental radiation source, wherein:
the local feature indicates a first probability that the non-environmental radiation source in the FOV caused the change in the detected levels of infrared radiation; and
the non-environmental radiation source corresponds to human motion;
extracting a global feature from the sample of the signal by a product of a feature parameter determined through training on a dataset to achieve a slow total variation and a rolling average value updated after every frame of the PIR, wherein the global feature indicates a second probability that an environmental radiation source caused the change in the detected levels of infrared radiation;
determining a score based on the local feature and the global feature; and
determining that the non-environmental radiation source has been detected in the FOV based on the score.