A vision-based deep learning approach for the detection and prediction of occupancy heat emissions for demand-driven control solutions

Tien, Paige Wenbin; Wei, Shuangyu; Calautit, John Kaiser; Darkwa, Jo; Wood, Christopher J.

doi:10.1016/j.enbuild.2020.110386

Cited by 71 publications

(49 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considerably, many deep learning methodologies for image and environmental sensorbased occupancy estimation research showed promising results [11,[28][29][30][31][32][33][34][35]. A people counting algorithm on thermal images-based on CNN was developed by Gomez et.al.…”

Section: Related Workmentioning

confidence: 99%

Thermal Imagery Feature Extraction Techniques and the Effects on Machine Learning Models for Smart HVAC Efficiency in Building Energy

et al. 2021

View full text Add to dashboard Cite

The control of thermostats of a heating, ventilation, and air-conditioning (HVAC) system installed in commercial and residential buildings remains a pertinent problem in building energy efficiency and thermal comfort research. The ability to determine the number of people at a particular time in an area is imperative for energy efficiency in order to condition only occupied regions and thermally deficient regions. In this study of the best features comparison for detecting the number of people in an area, feature extraction techniques including wavelet scattering, wavelet decomposition, grey-level co-occurrence matrix (GLCM) and feature maps convolution neural network (CNN) layers were explored using thermal camera imagery. Specifically, the pretrained CNN networks explored are the deep residual (Resnet-50) and visual geometry group (VGG-16) networks. The discriminating potential of Haar, Daubechies and Symlets wavelet statistics on different distributions of data were investigated. The performance of VGG-16 and ResNet-50 in an end-to-end manner utilizing transfer learning approach was investigated. Experimental results showed the classification and regression trees (CART) model trained on only GLCM and Haar wavelet statistic features, individually achieved accuracies of approximately 80% and 84%, respectively, in the detection problem. Moreover, k-nearest neighbors (KNN) trained on the combined features of GLCM and Haar wavelet statistics achieved an accuracy of approximately 86%. In addition, the performance accuracy of the multi classification support vector machine (SVM) trained on deep features obtained from layers of pretrained ResNet-50 and VGG-16 was between 96% and 97%. Furthermore, ResNet-50 transfer learning outperformed the VGG-16 transfer learning model for occupancy detection using thermal imagery. Overall, the SVM model trained on features extracted from wavelet scattering emerged as the best performing classifier with an accuracy of 100%. A principal component analysis (PCA) on the wavelet scattering features proved that the first twenty (20) principal components achieved a similar accuracy level instead of training on the whole feature set to reduce the execution time. The occupancy detection models can be integrated into HVAC control systems for energy efficiency and security systems, and aid in the distribution of resources to people in an area.

show abstract

Section: Related Workmentioning

confidence: 99%

Thermal Imagery Feature Extraction Techniques and the Effects on Machine Learning Models for Smart HVAC Efficiency in Building Energy

et al. 2021

View full text Add to dashboard Cite

show abstract

“…18 Original images are directly fed into the model, and hence pre-processing of training images are not required. 19 At the pre-processing stage, the initial step was to collect the input data for training and testing the model. Due to the lack of data or model from previous works, images were clustered from the Google search engine to form a dataset.…”

Section: Deep Learning and Computer Vision Techniquementioning

confidence: 99%

The impact of deep learning–based equipment usage detection on building energy demand estimation

Wei

Tien

et al. 2021

Building Services Engineering Research and Technology

Self Cite

View full text Add to dashboard Cite

As external temperatures and internal gains from equipment rise, office buildings’ cooling demand and issues are likely to increase. Solutions such as demand-driven controls can help minimise energy consumption and maintain thermal comfort in buildings by coordinating the real-time heating, ventilation and air-conditioning (HVAC) use to the requirements of the conditioned spaces. The present study introduces a real-time equipment usage detection and recognition approach for demand-driven controls using a deep learning method. A Faster R-CNN model was trained and deployed to a camera. The performance of this model was assessed through different evaluation metrics. Based on the initial field experiment results, a detection accuracy of 76.21% was achieved. To investigate the impact of the proposed approach on building heating and cooling energy demand, the case study building was modelled and simulated. The results showed that the deep learning–based method predicted up to 35.95% lower internal heat gains compared to static or ‘fixed’ schedules based on the set conditions. Practical Application: As the appliances and equipment in building spaces contribute to the internal heat gains, their usage can influence the building energy demand and indoor thermal environment. Linking equipment usage with occupants’ presence in space may not be fully accurate and may lead to the over- or under-estimation of heat emissions, especially when the space is unoccupied, and the equipment is powered ON or the opposite. This approach can be integrated with demand-driven controls for HVAC systems, which can minimise unnecessary building energy consumption while maintaining a comfortable indoor environment using computer vision and deep learning detection and recognition methods.

show abstract

“…Previous works, including [20,25], have shown these strategies' capabilities in sensing occupancy information through the count and location of occupants in spaces and aid demand-driven control systems. However, there is limited research on sensing the occupants' actual activities, which can affect the indoor environment conditions [26,27]. The activities of occupants can affect the internal heat gains (sensible and latent heat) in spaces directly [26] and indirectly towards other types of internal heat gains [27].…”

Section: Introduction and Literature Reviewmentioning

confidence: 99%

“…However, there is limited research on sensing the occupants' actual activities, which can affect the indoor environment conditions [26,27]. The activities of occupants can affect the internal heat gains (sensible and latent heat) in spaces directly [26] and indirectly towards other types of internal heat gains [27]. The real-time and accurate predictions of the occupants' heat emitted with various activity levels can be used to estimate better the actual heating or cooling requirements of a space.…”

Section: Introduction and Literature Reviewmentioning

confidence: 99%

Occupancy heat gain detection and prediction using deep learning approach for reducing building energy demand

Tien

Wei²,

Calautit³

et al. 2020

J. sustain. dev. energy water environ. syst.

Self Cite

View full text Add to dashboard Cite

The use of fixed or scheduled setpoints combined with varying occupancy patterns in buildings could lead to spaces being over or under-conditioned, which may lead to significant waste in energy consumption. The present study aims to develop a vision-based deep learning method for real-time occupancy activity detection and recognition. The method enables predicting and generating real-time heat gain data, which can inform building energy management systems and heating, ventilation, and air-conditioning (HVAC) controls. A faster region-based convolutional neural network was developed, trained and deployed to an artificial intelligence-powered camera. For the initial analysis, an experimental test was performed within a selected case study building's office space. Average detection accuracy of 92.2% was achieved for all activities. Using building energy simulation, the case study building was simulated with both 'static' and deep learning influenced profiles to assess the potential energy savings that can be achieved. The work has shown that the proposed approach can better estimate the occupancy internal heat gains for optimising the operations of building HVAC systems.

show abstract

A vision-based deep learning approach for the detection and prediction of occupancy heat emissions for demand-driven control solutions

Cited by 71 publications

References 50 publications

Thermal Imagery Feature Extraction Techniques and the Effects on Machine Learning Models for Smart HVAC Efficiency in Building Energy

Thermal Imagery Feature Extraction Techniques and the Effects on Machine Learning Models for Smart HVAC Efficiency in Building Energy

The impact of deep learning–based equipment usage detection on building energy demand estimation

Occupancy heat gain detection and prediction using deep learning approach for reducing building energy demand

Contact Info

Product

Resources

About