A novel occupant-centric stratum ventilation system using computer vision: Occupant detection, thermal comfort, air quality, and energy savings

Traditional ventilation and air conditioning systems typically operate on a predetermined schedule with fixed operating parameters. Occupant-centric control (OCC) strategies have been proposed to reduce system operation energy consumption without sacrificing thermal comfort. Indoor occupancy detection in real time is critical step successfully implementing the OCC strategy. Thus, deep learning-based computer vision method was adopted first of study, performance camera position were analyzed an office scenario. Next, strategy used regulate supply parameters outdoor volume stratum based monitored occupant number. The traditional static then compared two strategies: constant variable volume. Occupant results showed mean NRMSD for five most common relative positions occupants 0.1109, sitting back having lowest accuracy. Subjective response demonstrated that, when strategy, comfort improved by 43%–73%, perceived quality maintained at acceptable level, CO2 concentration less than 700 ppm, could be saved 2.3%–8.1%. Furthermore, lower occupancy, greater improvement savings. This research focused how responds dynamic changes provided insights into reducing unnecessary waste while maintaining