Video Instance Segmentation is All You Need for Linking Geographic Entities from Historical Maps
Xue Li Xia, Tao Zhang, Lorenz Hurni · 2024
Numerous historical research endeavors necessitate synthesizing information derived from multiple historical maps. Linking geographic entities across diverse maps has posed a persistent challenge for researchers. The conventional approach involves a two-step pipeline, initially detecting entities within individual maps and subsequently associating entities from different maps through a linking post-processing step. This paper introduces an innovative solution by conceptualizing historical maps as a 3D spatiotemporal volume. It advocates for simultaneous segmentation and association by employing video instance segmentation. The experimental findings demonstrate the superiority of the proposed method over the traditional approach, achieving a notable 0.2 F1-score improvement. Furthermore, its end-toend nature significantly streamlines the workflow for geographic entity alignment, thereby substantially enhancing the level of automation.