TY - RPRT
KW - Deep learning
KW - 3D geometry
KW - Semantic segmentation
KW - Photogrammetry
AU - Samir Touzani
AU - Marc Wudunn
AU - Samuel Fernandes
AU - Avideh Zakhor
AU - Rohullah Najibi
AU - Jessica Granderson
AB - <p>A building’s window-to-wall ratio (WWR) has critical influence on heat loss, solar gain, and daylighting levels, with implications for visual and thermal comfort as well as energy performance. However, in contrast to characteristics such as floor area, existing building WWRs are rarely available. In this work we present a machine learning based approach to parse windows from drone images and estimate the WWR. Our approach is based on firstly extracting the building 3D geometry from drone images, secondly performing semantic segmentation to detect windows and finally computing the WWR. Experiments show that our approach is effective in estimating WWR from drone images.</p>
DA - 09/2021
LA - eng
N2 - <p>A building’s window-to-wall ratio (WWR) has critical influence on heat loss, solar gain, and daylighting levels, with implications for visual and thermal comfort as well as energy performance. However, in contrast to characteristics such as floor area, existing building WWRs are rarely available. In this work we present a machine learning based approach to parse windows from drone images and estimate the WWR. Our approach is based on firstly extracting the building 3D geometry from drone images, secondly performing semantic segmentation to detect windows and finally computing the WWR. Experiments show that our approach is effective in estimating WWR from drone images.</p>
PY - 2021
TI - A MACHINE LEARNING APPROACH TO ESTIMATE  WINDOWS-TO-WALL RATIO USING DRONE IMAGER
ER -