Abstract
Purpose: The purpose of this study is to evaluate applicability of a model that can estimate MET in real time for multiple occupants as well as single occupants for application of PMV-based control in building environments. Method: Based on joint recognition stage and activity classification stage, a model that can estimate MET of multiple occupants from indoor images was proposed. Pose image dataset collected from the internet and self-captured in the lab was used for model training. For the performance evaluation of the model in single and multiple occupants condition, experiments were conducted in a test-bed on three activities; sitting, standing, and walking. The model was evaluated with the accuracy of real-time activity classification and representative MET estimation which was most frequent value in a given period of time. Result: The real-time activity classification accuracy of single occupant for the three activities was high in the order of sitting, standing, and walking. The representative MET estimation accuracy of single occupant applying the 1-min frequent value was 100% for all three activities. The representative MET estimation for multiple occupants showed an average accuracy of 88.8% in 1-min frequent and 100% accuracy in 5-min frequent. The result confirmed that the proposed model can be applied in the actual environment, when applying the representative MET value to multiple occupants.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call