Document Type

Conference Proceeding

Publication Title

BuildSys 2017 - Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments


In this poster we introduce the Commercial Occupancy Dataset (COD), a high-resolution long-term dataset of occupancy traces in a commercial office building spanning 9 months and covering zone-level occupancy for five different spaces containing more than 90,000 enter/exit events over this time period. Occupancy data in a building contains rich spatial-temporal information about the users and their usage of the space and facilities. However, obtaining accurate occupancy data is a very challenging task due to the limitation of existing sensing technologies. A novel depth-imaging based solution to estimate occupancy counts was deployed in five doorways of an office building to generate the dataset. The dataset has high resolutions in all three major dimensions: temporal, spatial and occupancy state. This allows applications such as building energy simulation, occupancy modeling and human-in-the-loop HVAC control which enhance energy efficiency and human comfort. Towards this objective, we provide a case study to demonstrate the utility of understanding occupancy.



Publication Date


Included in

Architecture Commons



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.