Abstract
Abstract. The authors developed a pipeline for the automatic georeferencing of older 1 : 25 000 topographic map sheets of Hungary. The first step is the detection of the corners of the map content, then the recognition of the sheet identifier. These maps depict geographic quadrangles whose extent can be derived from the sheet ID. The sheet corners are used as GCPs for the georeference.The whole process is implemented in Python, using various open source libraries: OpenCV for image processing, Tesseract for OCR and GDAL for georeferencing.1147 map sheets were processed with an average speed of 4 seconds per sheet. False detection of the corners is automatically filtered by geometric analysis of the detected GCPs, while the sheet IDs are validated using regular expressions. The error of corner detection is under 1% of the sheet size for 89% of the sheets, under 2% for 99%. The sheet ID recognition success rate is 75.9%.Although the system is finetuned to a specific map series, it can be easily adapted to any other map series having approximately rectangular frame.
Highlights
Old maps are great source of information about the past
The solutions presented in this paper have similarities to the ones above, but there are important differences as well: only open source software was used; the frame detection is based on Hough transformation and is refined by a simple convolutional filter to locally detect corners of thick frames; and the sheet ID detection is performed by OCR
The results show that the method described above is suitable for automatically georeferencing large amount of scanned topographic map sheets
Summary
Old maps are great source of information about the past. This true for map sheets of accurate country surveys: since the end of the 19th century, mapping methods became accurate enough to get reliable positional information, while the introduction of standardized map legends facilitate efficient information extraction. The information retrieved can be used in studies needing time series of georeferenced data such as landscape change or urban growth analysis. Using these maps in GIS environment requires their accurate georeferencing. While it is quite straightforward for one map sheet, georeferencing a whole series of map sheets may take tremendous time. The authors’ goal was to automatize this job using open source computer vision tools
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
