Leveraging ToF sensors for LED-based room occupancy detection
The idea is to use a distributed network of LED luminaires and cheap Time-of-Flight (ToF) sensors to generate an elevation map of the space being lit by the luminaires. Each light source is configured to emit light encoded with a predetermined modulation pattern within the network, and the scattered light (bouncing back from the objects or people within the room) is detected by the nearest (paired) ToF sensor which determines the height of the object below its corresponding lighting unit.
Another piece of the puzzle, a space characterization unit receives the distances logged by each sensor/luminaire pair and generates an elevation map to be compared with a reference map (say an empty office).
The technology can piggy-back on existing LED infrastructures, and in the future ToF sensors could be integrated into LDE-based luminaires to deliver real time occupancy detection and adaptive lighting at a lower cost than incumbent presence detection technologies.
Because the ToF sensors only detect light patterns, privacy of the occupants is preserved. Accurate mapping of the space could help determine the location as well as the height (sitting, standing of individuals and other objects in the room), while monitoring changes and movement detection.
To further develop and demonstrate the new technology, LESA has created two prototype testbeds, the “Smart Conference Room” operated at Rensselaer, and the “Smart Hospital Room”, located at the University of New Mexico. The testbeds are dedicated to taking LED lighting to new levels of cost-effective data generation and control using only the properties of the light itself.
Ultimately, LESA could integrate not only time-of-flight sensors but also other low-cost sensing technology, together with control software and machine learning capability, into the room’s LED fixtures.
Visit the Center for Lighting Enabled Systems & Applications (LESA) ERC at https://lesa.rpi.edu
Visit the Rensselaer Polytechnic Institute at www.rpi.edu
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
