Vision-based human activity recognition for reducing building energy demand. (November 2021)

• Record Type: Journal Article
• Authors: Tien, Paige Wenbin; Wei, Shuangyu; Calautit, John Kaiser; Darkwa, Jo; Wood, Christopher
• Other Names: Dwyer Tim guest-editor.
• Is Part Of: Building services engineering research & technology. Volume 42:Number 6(2021)
• Page Start: 691
• Page End: 713
• Publication Date: 2021-11
• Subjects: Deep learning -- occupancy activity detection -- building energy management -- heating, ventilation and air-conditioning systems -- building energy performance; Buildings -- Environmental engineering -- Periodicals; Buildings -- Environmental engineering -- Research -- Periodicals; Sanitary engineering -- Periodicals; 696.05
• DOI: 10.1177/01436244211026120
• Languages: English
• ISSNs: 0143-6244

Abstract

Occupancy behaviour in buildings can impact the energy performance and the operation of heating, ventilation and air-conditioning systems. To ensure building operations become optimised, it is vital to develop solutions that can monitor the utilisation of indoor spaces and provide occupants' actual thermal comfort requirements. This study presents the analysis of the application of a vision-based deep learning approach for human activity detection and recognition in buildings. A convolutional neural network was employed to enable the detection and classification of occupancy activities. The model was deployed to a camera that enabled real-time detections, giving an average detection accuracy of 98.65%. Data on the number of occupants performing each of the selected activities were collected, and deep learning–influenced profile was generated. Building energy simulation and various scenario-based cases were used to assess the impact of such an approach on the building energy demand and provide insights into how the proposed detection method can enable heating, ventilation and air-conditioning systems to respond to occupancy's dynamic changes. Results indicated that the deep learning approach could reduce the over- or under-estimation of occupancy heat gains. It is envisioned that the approach can be coupled with heating, ventilation and air-conditioning controls to adjust the setpoint based on the building space's actual requirements, which could provide more comfortable environments and minimise unnecessary building energy loads. Practical application: Occupancy behaviour has been identified as an important issue impacting the energy demand of building and heating, ventilation and air-conditioning systems. This study proposes a vision-based deep learning approach to capture, detect and recognise in real-time the occupancy patterns and activities within an office space environment. Initial building energy simulation analysis of the application of such an approach within buildings was performed. The proposed approach is envisioned to enable heating, ventilation and air-conditioning systems to adapt and make a timely response based on occupancy's dynamic changes. The results presented here show the practicality of such an approach that could be integrated with heating, ventilation and air-conditioning systems for various building spaces and environments.