U-M Develops Temperature Control System Using Thermal, 3-D Video Cameras

An automatic heating and cooling system that adjusts itself based on detection of users’ face temperatures has been developed and could offer a flexible solution to half-empty office buildings.
heat map of people on computer
U-M researchers have developed a heating and cooling system that adjusts itself based on how hot users’ faces are. // Photo courtesy of the University of Michigan

An automatic heating and cooling system that adjusts itself based on detection of users’ face temperatures has been developed and could offer a flexible solution to half-empty office buildings.

A group of researchers at Ann Arbor’s University of Michigan have developed the Human Embodied Autonomous Thermostat, or “HEAT,” with the hopes of providing a more personalized and efficient solution to temperature control.

The HEAT system pairs thermal and three-dimensional video cameras to determine whether an individual is hot or cold based on their facial temperature – blood vessels expand to radiate heat when people are too hot, raising facial temperature, and constrict when people are too cold, cooling the face.

Next, the system relays the information to a predictive model which compares it with information about the individual’s thermal preferences. The system then determines and sets the temperature that will keep the most individuals in the area comfortable while expending minimal energy.

“COVID presents a variety of new climate control challenges as buildings are occupied less consistently and people struggle to stay comfortable while wearing masks and other protective gear,” says Carol Menassa, project principal investigator, study co-author, and associate professor of civil and environmental engineering.

“HEAT could provide an unobtrusive way to maximize comfort while using less energy. The key innovation here is that we’re able to measure comfort without requiring users to wear any detection devices and without the need for a separate camera for each occupant.”

When first installed, individuals give the system periodic feedback by using their smartphones to choose between a three-point scale of “too hot,” “too cold,” or “comfortable.” HEAT learns their preferences and begins operating independently after a few days.

The research team is working with power company Southern Company Research and Development to begin testing HEAT at Southern’s Alabama offices. In this setting, the test cameras will be mounted on tripods in the corner of rooms, but Menassa explains that in the future, cameras will be placed in less obtrusive and more permanent locations.

“The cameras we’re using are common and inexpensive, and the model works very well in a residential context,” says Vineet Kamat, study co-author and U-M professor of civil and environmental engineering, and electrical engineering and computer science. “Internet-enabled thermostats that detect you and learn from you have sort of built a platform for the next phase, where there’s no visible thermostat at all.”

While the cameras will be focusing on occupants, they do not identify individuals, and all footage is deleted immediately after processing.

In a pilot study conducted in partnership with the U-M school of nursing, the research group explored how the system can be used to provide comfort for nurses working in health care environments.

“The COVID-19 pandemic requires nurses and other hospital workers to wear a lot of protective gear, and they’ve struggled to stay comfortable in the fast-paced hospital environment,” says Eunshin Byon, study co-author and associate professor of industrial operations and engineering at U-M. “The HEAT system could be adapted to help them stay comfortable by adjusting room temperature or even by signaling to them when they need to take a break.”

The research team also includes former U-M graduate research assistance Da Li, who is presently an assistance professor of civil engineering at Clemson University. The team, which has filed patent applications related to the technology, was supported by the National Science Foundation. HEAT is available as a licensable technology through the U-M Office of Technology Transfer.

Facebook Comments