Automatic Georeferencing of Topographic Raster Maps

Abstract

In recent years, many scientific institutions have digitized their collections, which often include a large variety of topographic raster maps. These raster maps provide accurate (historical) geographical information but cannot be integrated directly into a geographical information system (GIS) due to a lack of metadata. Additionally, the text labels on the map are usually not annotated, making it inefficient to query for specific toponyms. Manually georeferencing and annotating the text labels on these maps is not cost-effective for large collections. This work presents a fully automated georeferencing approach based on text recognition and geocoding pipeline. After recognizing the text on the maps, publicly available geocoders were used to determine a region of interest. The approach was validated on a collection of historical and contemporary topographic maps. We show that this approach can geolocate the topographic maps fairly accurately, resulting in an average georeferencing error of only 316 m (1.67%) and 287 m (0.90%) for 16 historical maps and 9 contemporary maps spanning 19 km and 32 km, respectively (scale 1:25,000 and 1:50,000). Furthermore, this approach allows the maps to be queried based on the recognized visible text and found toponyms, which further improves the accessibility and quality of the collection.

Learning the past landscape of Yogyakarta city from historical maps

“…A georeferencing method may use any defined area, including the entire planet, a certain nation, or any other defined area.The digitization of historical maps has allowed researchers to access high-quality geographic data from the past. These maps are often the only reliable source of digitized data, making them a valuable resource 42 . Historical maps must be preserved in order to fully realize their potential as cartographic works with all of their unique characteristics 43 .…”

Georeferencing for Planning Underground Networks

“…The management of geo-referenced information may include information that needs to be verified due to possible failures in the on-site visit; previous works evaluate labels and filters to evidence buildings in specific areas [23]. Articulating raster maps into a single system could be a non-trivial task for institutions handling geo-referenced information and requiring integration into a geographic information system (GIS) because of scarce metadata [24].…”

“…Objectives Electricity Drinking Water Data Gas Transport Other Garcia, 2023 [6] Power Network Planning ✓ ✓ Kim, 2023 [16] Healthcare accessibility ✓ ✓ ✓ Wu, 2023 [15] Urban Development ✓ ✓ ✓ Gaugl, 2023 [14] Power Network Planning ✓ ✓ Kersapati, 2023 [17] Urban Management ✓ ✓ ✓ Kim, 2022 [25] Small unmanned aircraft ✓ ✓ Song, 2022 [23] Remote sensing -Urban planning ✓ ✓ Hacar, 2022 [22] Urban planning ✓ ✓ Hellekes, 2022 [20] Urban Planning ✓ ✓ ✓ Zourlidou, 2022 [19] Traffic Engineering ✓ ✓ ✓ Milleville, 2022 [24] Gerreferencing…”

The Results of Digitizing Historical Maps: Comparison of Lithuanian Land-Use Structure in the 19th and 21st Centuries

“…Automatic digitization/vectorization methods require expert knowledge and are not easily usable for non-expert users [21]. Automated or semi-automated georeferencing is usually used for maps with a known spatial reference system [14,22], for maps that have colourful objects and areas [23,24], and with toponyms by using text recognition tools [25]. For automated digitization, ArcGIS software [22], geocoding methods [23] and machine learning [10] can be used.…”