MapSAM2: Adapting SAM2 for Automatic Segmentation of Historical Map Images and Time Series
Open Access
- 27 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-11
Abstract
Historical maps are unique and valuable archives that document geographic features across different time periods. However, automated analysis of historical map images remains a significant challenge due to their wide stylistic variability and the scarcity of annotated training data. Constructing linked spatio-temporal datasets from historical map time series is even more time-consuming and labor-intensive, as it requires synthesizing information from multiple maps. Such datasets are essential for applications such as dating buildings, analyzing the development of road networks and settlements, studying environmental changes etc. We present MapSAM2, a unified framework for automatically segmenting both historical map images and time series. Built on a visual foundation model, MapSAM2 adapts to diverse segmentation tasks with few-shot fine-tuning. Our key innovation is to treat both historical map images and time series as videos. For images, we process a set of tiles as a video, enabling the memory attention mechanism to incorporate contextual cues from similar tiles, leading to improved geometric accuracy, particularly for areal features. For time series, we introduce the annotated Siegfried Building Time Series Dataset and, to reduce annotation costs, propose generating pseudo time series from single-year maps by simulating common temporal transformations. Experimental results show that MapSAM2 learns temporal associations effectively and can accurately segment and link buildings in time series under limited supervision or using pseudo videos. We release both our dataset and code to support future research.Keywords
All Related Versions
Funding Information
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (200021_192018)
This publication has 33 references indexed in Scilit:
- Fine-Tune Smarter, Not Harder: Parameter-Efficient Fine-Tuning for Geospatial Foundation Models2025
- Few-Shot Segmentation of Historical Maps via Linear Probing of Vision Foundation Models2025
- A novel method to assess spatio-temporal habitat availability for a generalist indicator species group in human-modified landscapesLandscape Ecology, 2025
- Archetypes of settlement development on the Swiss Plateau: Identification, description and predictionCities, 2025
- Vectorizing historical maps with topological consistency: A hybrid approach using transformers and contour-based instance segmentationInternational Journal of Applied Earth Observation and Geoinformation, 2024
- Self-prompting Large Vision Models for Few-Shot Medical Image Segmentation2023
- A fast and effective deep learning approach for road extraction from historical maps by automatically generating training data with symbol reconstructionInternational Journal of Applied Earth Observation and Geoinformation, 2022
- ICDAR 2021 Competition on Historical Map Segmentation2021
- Building Linked Spatio-Temporal Data from Vectorized Historical Maps2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015