.png){kind=icon}
.png){kind=icon}
Return
A deep learning method for building facade parsing utilizing improved SOLOv2 instance segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.enbuild.2023.113275.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Energy consumption simulation and renovation of existing buildings require accurate acquisition of building facade features which mostly relies on time-consuming manual calculations based on architectural drawings. In this article, we proposed an automated deep learning-based approach based on the SE module and BiFPN to achieve precise and efficient facade feature extraction. The approach eliminated the image distortion of building facades and then enabled accurate segmentation of windows and accessory structures even under the situation of occlusion and reflection. The improved SOLOv2 algorithm resulted in a high mean average precision of 93% for window segmentation, leading to a more precise window-to-wall ratio estimation with a mean absolute error of 2.9% than the experts' estimation and existing deep learning-based methods. Considering the accurate results of facade parsing, our method can be utilized for city-level building feature extraction, providing theoretical and practical references for urban building energy simulation, urban renewal, and building health examination.
Keywords:
Building facade
Deep learning
Energy consumption
Feature parsing
Instance segmentation
Window -to -wall ratio (WWR)