RouteExtract: A Modular Pipeline for Extracting Routes from Paper Maps
This addresses a domain-specific problem for hikers and sightseers who rely on paper maps, but it is incremental as it combines existing techniques like georeferencing and U-Net segmentation.
The paper tackles the problem of extracting navigable trails from scanned paper maps to enable GPS-based navigation, showing that their pipeline can robustly recover trail networks from diverse map styles and generate GPS routes suitable for practical use.
Paper maps remain widely used for hiking and sightseeing because they contain curated trails and locally relevant annotations that are often missing from digital navigation applications such as Google Maps. We propose a pipeline to extract navigable trails from scanned maps, enabling their use in GPS-based navigation. Our method combines georeferencing, U-Net-based binary segmentation, graph construction, and an iterative refinement procedure using a routing engine. We evaluate the full end-to-end pipeline as well as individual components, showing that the approach can robustly recover trail networks from diverse map styles and generate GPS routes suitable for practical use.