Occupancy information is important to building facility mangers in terms of predictive control, safety, as well as the indoor environment quality. Previous works have addressed different occupancy counting and estimation solutions in different buildings or spaces. In this study, we build up a test bed using the existing university lecture theatres to develop and compare three different occupancy counting methodologies. A novel CO2 based identification model is developed using CO2 sensor data and EnergyPlus simulation; a PTZ-Camera based face recognition algorithm and lastly a video based occupancy counting methodology. We attempt to address the occupancy counting challenge in educational building deployment scenario with large groups of people entering and leaving. Experiments have been conducted for one week with 5 minute data reporting interval. The results will be compared with the manually counted ground truth data. The results show that the PTZ-camera based face recognition has the most stable and highest accuracy with an R² of 0.99; followed by the CO2 based identification model with an R² of 0.84.
Citation: 2017 Annual Conference, Long Beach, CA, Conference Papers
Product Details
- Published:
- 2017
- Number of Pages:
- 8
- Units of Measure:
- Dual
- File Size:
- 1 file , 750 KB
- Product Code(s):
- D-LB-17-C021
