Scalable Evaluation of 3D City Models

Abstract

The generation of 3D building models from Very High Resolution geospatial data is now an automatized procedure. However, urban areas are very complex and practitioners still have to visually assess the correctness of these models and detect reconstruction errors. We proposed an approach for automatically evaluating the quality of 3D building models. It is cast as a supervised classification task based on a hierarchical taxonomy and multimodal handcrafted features (building geometry, optical images, height data). In this paper, we evaluate how the urban area composition impacts prediction transferability and scalability of our framework to unseen scenes. This allows to define minimal feature and training sets for a problem where no benchmark data has been released so far.

Infrastructure for 3D Modeling of Historical Fountains in Istanbul with GIS-Based Procedural Approach

“…Large city-scale studies can only yield results by waiting for certain processing times [36]. Even though the recent software that has been developed in this field and the automation of building-model production is used, the individual examinations, corrections, and improvements in the final products are processes that require human intervention and take a lot of time [41].…”