Large Scale Architectural Asset Extraction from Panoramic Imagery
Permanent link to this recordhttp://hdl.handle.net/10754/655517
MetadataShow full item record
AbstractWe present a system to extract architectural assets from large scale collections of panoramic imagery. First, we automatically rectify and crop parts of the panoramic image that contain dominant planes. Second, we use object detection to extract assets such as facades and windows. Third, we use various tools to determine attributes of the assets to determine the asset quality and index the assets for search. Fourth, we provide a user interface to visualize and query assets. Finally, we present applications to urban modeling and texture synthesis.