Abstract
Abstract. As more cities are starting to experience the urban heat islands effect, knowledge about the energy emitted from building roofs is of primary importance. Since this energy depends both on roof orientations and materials, we tackled both issues by analysing sensor data from multispectral, thermal infrared, high-resolution RGB, and airborne laser datasets (each with different spatial resolutions) of a council in Perth, Australia. To localise the roofs, we acquired building outlines that had to be updated using the normalised digital surface model, the NDVI and the planarity. Then, we computed a semantic 3D model of the study area, with roof detail analysis being a particular focus. The main objective of this study, however, was to classify three commonly used roofing materials: Cement tiles, Colorbond and Zincalume by combining the multispectral and thermal infrared image bands while the high-resolution RGB dataset was used to provide additional information about the roof texture. Three types of image segmentation approaches were evaluated to assess any differences while performing the material classification; pixel-wise, superpixel-wise and building-wise image segmentation. Due to the limited amount of labelled data, we extended the dataset by labelling data ourselves and merged Colorbond and Zincalume into one separate class. The supervised classifier Random Forest was applied to all reasonable configurations of segmentation kinds, numbers of classes, and finally, keeping track of the added value of principal component analysis.
Highlights
The land use coverage in cities affects the quality of living and as cities grow, the amount of vegetation is often reduced to make space for buildings
We encountered holes in the Normalised Digital Surface Model (nDSM) that had occurred during the Digital Surface Model (DSM) sampling from the Light Detection and Ranging (LiDAR) point cloud and had caused false negatives
We utilised three labelled datasets; the original provided by the City of Melville that consisted of the three roofing materials Cement tiles, Colorbond and Zincalume, the original but consisting of the two roofing materials Cement tiles and Metallic, and an extended dataset consisting the two aforementioned materials
Summary
The land use coverage in cities affects the quality of living and as cities grow, the amount of vegetation is often reduced to make space for buildings. Due to the decreased amount of vegetation, areas within cities that have an increased temperature compared to their surrounding rural areas, so called urban heat islands (Oke, 1982), are on the rise in major cities. Knowledge about materials found on buildings is valuable information for municipalities and authorities when dealing with urban planning. By knowing which roofing materials that are present in areas located within urban heat island, municipalities and authorities can create strategies to counter the effect. This kind of information have a spatial aspect and are often based on remote sensing datasets. Combining data from multiple sensors can provide with further information for urban studies (Dimmeler et al, 2013; Kumar et al, 2015)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
