Window to Wall Ratio Detection using SegFormer
This work addresses the lack of data for building energy and environmental simulations, which often rely on assumed WWR values, by providing a method to estimate WWR from images.
The paper tackled the problem of estimating Window to Wall Ratios (WWR) for building performance assessment by using semantic segmentation on street view images, demonstrating the potential of adapting computer vision techniques to architectural applications.
Window to Wall Ratios (WWR) are key to assessing the energy, daylight and ventilation performance of buildings. Studies have shown that window area has a large impact on building performance and simulation. However, data to set up these environmental models and simulations is typically not available. Instead, a standard 40% WWR is typically assumed for all buildings. This paper leverages existing computer vision window detection methods to predict WWR of buildings from external street view images using semantic segmentation, demonstrating the potential for adapting established computer vision technique in architectural applications