Predicting room occupancy with a single passive infrared (PIR) sensor through behavior extraction


Passive infrared sensors have widespread use in many applications, including motion detectors for alarms, lighting systems and hand dryers. Combinations of multiple PIR sensors have also been used to count the number of humans passing through doorways. In this paper, we demonstrate the potential of the PIR sensor as a tool for occupancy estimation inside of a monitored environment. Our approach shows how flexible nonparametric machine learning algorithms extract useful information about the occupancy from a single PIR sensor. The approach allows us to understand and make use of the motion patterns generated by people within the monitored environment. The proposed counting system uses information about those patterns to provide an accurate estimate of room occupancy which can be updated every 30 seconds. The system was successfully tested on data from more than 50 real office meetings consisting of at most 14 room occupants.

Publication DOI:
Divisions: College of Engineering & Physical Sciences
College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: -
Event Title: 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Event Type: Other
Event Dates: 2016-09-12 - 2016-09-16
Uncontrolled Keywords: behavior extraction,monitoring,occupancy estimation,PIR sensors,Information Systems,Hardware and Architecture,Computer Networks and Communications,Software,Human-Computer Interaction
ISBN: 978-1-4503-4461-6
Last Modified: 18 Jun 2024 07:52
Date Deposited: 02 Nov 2016 13:25
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Conference contribution
Published Date: 2016-09-12
Accepted Date: 2016-09-01
Authors: Raykov, Yordan P. (ORCID Profile 0000-0003-0753-717X)
Ozer, Emre
Dasika, Ganesh
Boukouvalas, Alexis
Little, Max A. (ORCID Profile 0000-0002-1507-3822)



Version: Accepted Version

Export / Share Citation


Additional statistics for this record