Gathering occupancy data is considered as one of the grand challenges in building information modeling. Direct occupancy detection methods, such as the typical passive infrared (PIR) motion detectors detect motion rather than presence and are difficult to retrofit into existing buildings. In-direct methods, e.g., measuring CO2 levels as a proxy for occupant presence require calibration and training data to perform effectively.
In our work, we capitalize on the pervasiveness of mobile devices with Bluetooth (BT) functionality, and use this BT signal to infer occupant presence. We use low-cost hardware based on the Raspberry Pi microcomputer, and apply our approach in four typical building applications: (1) presence detection of a specific occupant, (2) characterization of a shared office, (3) counting occupants, and (4) occupancy density estimation of a building.