A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Real-time detection method of window opening behavior using deep learning-based image recognition in severe cold regions
https://orcid.org/0000-0003-3158-6123
Graphical abstract Display Omitted
Highlights The proposed method can be applied to all window types and does not require the manual adjustment of threshold values according to different weather conditions. The prediction accuracy of the proposed method in the case study reaches 97.79%. The features of window opening behavior for a teaching building in severe cold regions are explored. Occupants of teaching buildings in severe cold regions in the transition season prefer a large opening angle (45°∼180°).
Abstract The building industry plays an important role in the effort to achieve carbon neutrality, and window opening behavior is a major contributor to building energy consumption. In severe cold regions, opening windows during the heating period causes energy waste. If the window opening behavior can be monitored in real time, then the occupants' energy use behavior can be guided to reduce energy waste. This paper proposes a window opening behavior monitoring method using a deep learning-based image recognition model that can identify the window state based on real-time video and was validated in a case study based on outdoor thermal and wind data. A teaching building with casement windows was used as a case study. The results showed that the occupants preferred a large window opening angle (45°∼180°), which is a choice that significantly affects the building energy consumption. The prediction accuracy of the proposed method can reach 97.79%, which also serves to avoid the difficulty of manually calibrating the pixel threshold and realize real-time feedback. This method has a wide range of application scenarios that enable us to obtain window opening behavior to improve the building performance simulation accuracy and guide occupants' energy consumption behavior.
Real-time detection method of window opening behavior using deep learning-based image recognition in severe cold regions
https://orcid.org/0000-0003-3158-6123
Graphical abstract Display Omitted
Highlights The proposed method can be applied to all window types and does not require the manual adjustment of threshold values according to different weather conditions. The prediction accuracy of the proposed method in the case study reaches 97.79%. The features of window opening behavior for a teaching building in severe cold regions are explored. Occupants of teaching buildings in severe cold regions in the transition season prefer a large opening angle (45°∼180°).
Abstract The building industry plays an important role in the effort to achieve carbon neutrality, and window opening behavior is a major contributor to building energy consumption. In severe cold regions, opening windows during the heating period causes energy waste. If the window opening behavior can be monitored in real time, then the occupants' energy use behavior can be guided to reduce energy waste. This paper proposes a window opening behavior monitoring method using a deep learning-based image recognition model that can identify the window state based on real-time video and was validated in a case study based on outdoor thermal and wind data. A teaching building with casement windows was used as a case study. The results showed that the occupants preferred a large window opening angle (45°∼180°), which is a choice that significantly affects the building energy consumption. The prediction accuracy of the proposed method can reach 97.79%, which also serves to avoid the difficulty of manually calibrating the pixel threshold and realize real-time feedback. This method has a wide range of application scenarios that enable us to obtain window opening behavior to improve the building performance simulation accuracy and guide occupants' energy consumption behavior.
Real-time detection method of window opening behavior using deep learning-based image recognition in severe cold regions
https://orcid.org/0000-0003-3158-6123
Graphical abstract Display Omitted
Highlights The proposed method can be applied to all window types and does not require the manual adjustment of threshold values according to different weather conditions. The prediction accuracy of the proposed method in the case study reaches 97.79%. The features of window opening behavior for a teaching building in severe cold regions are explored. Occupants of teaching buildings in severe cold regions in the transition season prefer a large opening angle (45°∼180°).
Abstract The building industry plays an important role in the effort to achieve carbon neutrality, and window opening behavior is a major contributor to building energy consumption. In severe cold regions, opening windows during the heating period causes energy waste. If the window opening behavior can be monitored in real time, then the occupants' energy use behavior can be guided to reduce energy waste. This paper proposes a window opening behavior monitoring method using a deep learning-based image recognition model that can identify the window state based on real-time video and was validated in a case study based on outdoor thermal and wind data. A teaching building with casement windows was used as a case study. The results showed that the occupants preferred a large window opening angle (45°∼180°), which is a choice that significantly affects the building energy consumption. The prediction accuracy of the proposed method can reach 97.79%, which also serves to avoid the difficulty of manually calibrating the pixel threshold and realize real-time feedback. This method has a wide range of application scenarios that enable us to obtain window opening behavior to improve the building performance simulation accuracy and guide occupants' energy consumption behavior.
Real-time detection method of window opening behavior using deep learning-based image recognition in severe cold regions
Sun, Cheng (author) / Guo, Xumiao (author) / Zhao, Tianyu (author) / Han, Yunsong (author)
Energy and Buildings ; 268
2022-05-18
Article (Journal)
Electronic Resource
English
Fast-assembly type anti-freezing out-opening window suitable for severe cold area
| European Patent Office | 2024
Deep Learning Automatic Opening of Window of Vehicle using Deep Learning for Prevention of Drowing
| European Patent Office | 2023
Fireproof and heat-preservation structure for outer wall and door window opening in severe cold area
| European Patent Office | 2021