A zone-level occupancy counting system for commercial office spaces using low-resolution time-of-flight sensors

• Published in: Energy and buildings 2021-12, Vol.252 (C), p.111390, Article 111390
• Main Authors: Lu, Hao, Tuzikas, Arunas, Radke, Richard J.
• Format: Article
• Language: English
• Subjects: Algorithms; Energy conservation; Indoor occupancy counting; Localization; Occupancy; Sensors; Time-of-flight sensors; Urban environments
• ISSN: 0378-7788; 1872-6178
• DOI: 10.1016/j.enbuild.2021.111390

[Display omitted] •We designed a low-resolution time-of-flight system for accurate occupancy counting.•The system handles multiple people walking in arbitrary directions.•The system is evaluated in realistic simulations and a physical installation. Understanding the locations of occupants in a commercial built environment is critical for realizing energy savings by delivering lighting, heating, and cooling only where it is needed. In this paper, we present an indoor occupancy counting system using a sparse array of inexpensive, low-resolution, and privacy-preserving time-of-flight sensors. We develop and validate an algorithm for zonal occupancy counting that can deal with multiple people walking underneath the sensors in arbitrary directions, and evaluate the system both in realistic simulations of office spaces and in a real-world installation. We found that our system has an error rate of around 0.4%, resulting in highly accurate person localization and zone counting using only a few sensors per space.