Classification of photo-realistic 3D window views in a high-density city: The case of Hong Kong

Abstract

Window view is an intimate medium between occupants and nature, especially in high-density cities like Hong Kong; and thus belongs to the quality of a house or apartment. In literature, views of nature have been quantitatively studied in satellite images and cars’ cameras at a macro or micro level, respectively. Researchers found that window views are vital to the occupants’ physical and psychological health, urban environment optimization, urban planning and development policies, and CIM semantic enrichment for smart cities. However, as an essential supplement to the greenery view information hub at a mesoscale, few studies on efficient visualization and classification of window views at the urban level seem available. This paper presents an approach that captures and classifies photo-realistic views at the windows in a 3D photogrammetric city model. First, the geometries of buildings and their windows are ‘triangulated’ from 3D photogrammetric and 2D digital maps. Then, we annotate the 3D array of window locations of each facade in batch. Finally, the view at each window is captured and analyzed by computer programs automatically. We applied the proposed approach to the 3D model of Hong Kong Island and found satisfactory results for identifying nature scenes or urban scenes. Once massively adopted, the presented approach can offer novel geographic indicators for billions of urban inhabitants and the Architecture, Engineering, Construction, and Operation (AECO) industry.