MapStyleSeg full code
Digitizing and analyzing historical topographic maps is essential for spatial analysis in GIS, yet traditional methods are labor-intensive and challenged by unclear boundaries and inconsistent map styles. We address these challenges by proposing a new Map Style Segmentation (MapStyleSeg) method that employs unsupervised domain adaptation (UDA) from deep learning (DL) to enhance cross-style, cross-year automatic map segmentation and conversion. Our method, MapStyleSeg, is exemplified through training on a fully annotated topographic map of Taiwan in 2017 and applied to a historical topographic map from 2001 lacking annotations. We also evaluated different encoder-decoder architectures and loss functions. Our results show that using the ResNet-101 backbone with the SegFormer decoder and a mix of focal and Dice loss yields the best performance: 94.94% overall accuracy (Acc), 81.8% mean Intersection over Union (mIoU), outperforming standard U-Net models without UDA (88.23% Acc, 49.3% mIoU). Our approach addresses the challenges of analyzing historical maps with varying styles, further advancing GIS methodologies and offering valuable insights for urban planning, environmental monitoring, and decision-making processes. This work highlights the importance of merging DL with GIS to handle complex spatial datasets efficiently, paving the way for future interdisciplinary research in geographic information science.