Content-based Image Retrieval for Map Georeferencing

Abstract

Abstract. In recent years, libraries have made great progress in digitising troves of historical maps with high-resolution scanners. Providing user-friendly information access for cultural heritage through spatial search and webGIS requires georeferencing of the hundreds of thousands of digitised maps.Georeferencing is usually done manually by finding “ground control points”, locations in the digital map image, whose identity is unambiguous and can easily be found in modern-day reference geodata/mapping data. To decide whether two symbols from different maps describe the same object, their semantic and spatial relations need to be matched. Automating this process is the only feasible way to georeference the immense quantities of maps in conceivable time. However, automated solutions for spatial matching quickly fail when faced with incomplete data – which is the greatest challenge when comparing maps of different ages or scales.These problems can be overcome by computing map similarity in the image domain. Treating maps as a special case of image processing allows efficient and robust matching and thus identification of geographical regions without the need to explicitly model semantics. We propose a method to encode worldwide reference VGI mapping data as image features, allowing the construction of an efficient lookup index. With this index, content-based image retrieval can be used for both geolocating a given map for georeferencing with high accuracy. We demonstrate our approach on hundreds of map sheets of different historical topographical survey map series, successfully georeferencing most of them within mere seconds.

An ontology‐based semantic description model of ubiquitous map images

“…Consequently, they differ significantly in symbol design, color schemes, map layout, and other map elements. They impose great challenges for machine‐centered tasks such as semantic retrieval (Luft & Schiewe, 2021; Walter et al., 2013), content description and analysis (Degbelo, 2021a; Fish, 2020; Scheider et al., 2014), and information extraction (Tavakkol et al., 2019; Uhl et al., 2018). The main reason lies in the semantic gap between the simple physical form and the complex connotation of UMIs, which impedes their in‐depth applications.…”

Unsupervised historical map registration by a deformation neural network

“…Unlocking spatial information at different times enables us to monitor the trajectory of spatio-temporal dynamics of features in the past, which can support studies and analysis in various fields like urban planning, environmental sciences, and ecology. Existing works about geo-referencing historical maps focus on determining their locations by comparing them with other geo-referenced data [14,15,1]. However, even after being geo-referenced, features from maps at different time stamps can be spatially misaligned, due to different surveying processes, generalization procedures, production conditions, and map distortions.…”