Creating High Resolution, Three-Dimensional Digital Models of Historic Urban Neighborhoods from Sanborn Fire Insurance Maps using Machine Learning

Keywords: Sanborn maps, 3D city modeling, digital humanities, historical maps, urban development
Abstract Type: Paper Abstract

Abstract

Sanborn Fire Insurance maps contain a wealth of building-level information about US cities dating back to the late 19th century. They are a valuable resource for studying changes in urban environments, such as the legacy of urban highway construction and urban renewal in the 20th century. However, it is a challenge to automatically extract the building-level information effectively and efficiently from Sanborn maps because of the large number of map entities and the lack of appropriate computational methods to detect these entities. This paper describes a scalable and semi-automated framework for extracting urban information from Sanborn maps and cartographically reconstructing historic urban neighborhoods. The workflow involves three steps. The first step georeferences Sanborn maps to a geographic coordinate system. In the second step, we use machine learning methods to automatically identify building footprints and properties on the georeferenced maps. The third step uses the information obtained to create a 3D visualization of the historic neighborhoods. We demonstrate our methods using Sanborn maps for two neighborhoods in Columbus, Ohio, USA that were bisected by highway construction in the 1960s. Quantitative and visual analysis of the results suggest high accuracy of the extracted building-level information, and we illustrate how to visualize pre-highway neighborhoods.