Shadow Detection of Building Facades for Energy Efficiency Using YOLOv8 and Segmentation Techniques

Effectively utilizing natural light in architectural design has a substantial impact on energy usage in addition to improving aesthetic appeal. This study presents a novel use of shadow detection for energy-saving projects and architects. We use two different AI approaches, segmentation techniques and YOLOv8, to automate recognizing shadows thrown on building facades. This paper starts with a thorough explanation of the importance of shadow analysis in architectural design, highlighting how it can maximize natural lighting and reduce energy use. First, we study how to recognize shadows on building facades using YOLOv8, a state-of-the-art object identification framework. This paper discusses how YOLOv8 was modified for this particular use case. Secondly, we explore Otsu's threshold segmentation method as an alternative approach to shadow detection. The YOLOv8 shadow detection approach is favored for its versatility across diverse input image types, enabling effective shadow detection even in dissimilar images. It efficiently identifies shadows by generating bounding boxes that indicate the degree of shadow accuracy. Otsu's threshold image segmentation is recommended for situations where additional image processing is intended, such as determining shadow areas using methods like background subtraction.