Introducción a Map Warper

Abstract. Historical maps consist an important source of information and a research tool for several researchers of various scientific fields, especially the humanities (Michev 2016), who are working on the geographic analysis of the environment. For them, the digital comparative analysis of historical and modern maps offers a variety of benefits. It expands the scope of their research, providing them the opportunity to study the geometric and thematic properties of the maps, or they use maps constructed on different periods to detect and determine changes in the physical environment, border changes, or changes on the toponyms (e.g. Boutoura & Livieratos, 1986, 2006; Livieratos, 2006; Tsorlini et al, 2010). This is really essential, especially when these changes are only apparent through maps and no other written source exists (Tsorlini et al, 2017).Historical maps in different forms, independent or embedded in books, atlases or map series, are located in map collections mainly in libraries worldwide. These cartographic materials abroad are stored in specific departments in the libraries, where specialized personnel deals with them and is responsible for their management, preservation and demonstration to the public. This is not the case for our country, since many historical maps and other related cartographic material in libraries, remain almost unknown to researchers and generally to the public. Sometimes, there are difficulties even to detect historical maps in the library’s system, because they are documented and recorded following specific rules related mainly to traditional descriptive methods applied in book-keeping and book-archiving (Boutoura, 2014). As a consequence, there are important maps, who haven’t been studied or analysed until today and their important value has not been exploited yet in library’s environment.One of the most important libraries in Greece and the second in size after the National Library, is the Library and Information Centre of the Aristotle University of Thessaloniki (AUTH Library). The cartographic material located in AUTH Library has not been documented and studied properly in all its size and the cartographic wealth has not been exploited in Library’s environment, until its cooperation with the Laboratory of Cartography and Geographical Analysis which was realized recently. In the frame of this cooperation, a research project was developed focusing on one of the AUTH Library’s collections, the very important Ioannis Tricoglou Library, with the aim to collect, document and organize the cartographic material found in this collection, in an information system, which will give the opportunity to researchers and to the general public to search for maps, independent or embedded in books, and to find relevant information for them through an easy and user-friendly digital environment. In this way, historical maps and other cartographic material located in Library’s collections will be demonstrated to researchers and the general public, presenting and promoting also the cartographic wealth of the library.The main stages of this project are: a) the collection and documentation of the maps found in Ioannis Tricoglou Library, b)the proper transformation of these data to provide information through a database, c) the connection of the maps in thedatabase with other related textual and pictorial sources, in order to enrich the information provided for the maps not onlyfor researchers and students, but also for the library’s staff, simplifying in this way the searching procedure and finally(Tsorlini et al, 2018a), and finally, d) the development of a user-friendly digital environment, which will provide accessto historical maps and relevant cartographic material located in Ioannis Tricoglou Library. Emphasis on this project isgiven to the maps which were found inside the books, since they were not recorded and documented correctly, they werenot digitized in the proper way, thus it was impossible to detect them through the existing library’s system (Tsorlini et al,2018b).In this paper, we will analyse shortly the main stages of the project and we will discuss the problems appeared during the whole procedure. Moreover, we will present its results, which can assist to the improvement of the library’s searching system and to the demonstration of the unknown cartographic wealth of the library to the academic community and general public.

Digitizing historical topographic maps is essential for spatial analysis in GIS; however, conventional methods for digitizing these maps are labor-intensive and challenging due to non-explicit 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 by training on a fully annotated topographic map of Taiwan in 2017 and applying it to a 2001 topographic map without 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 digitizing historical maps with varying styles, further advancing GIS digitization of historical maps, and offering useful information for urban planning, environmental monitoring, and decision-making processes. This work highlights the novel use of DL algorithms to automate complex GIS data processing that transforms historical maps into spatial datasets.

Historical topographic maps are an important source of a visual record of the landscape, showing geographical elements such as terrain, elevation, rivers and water bodies, roads, buildings, and land use and land cover (LULC). Historical maps are scanned to their digital representation, a raster image. To quantify different classes of LULC, it is necessary to transform scanned maps to their vector equivalent. Traditionally, this has been done either manually, or by using (semi)automatic methods of clustering/segmentation. With the advent of deep neural networks, new horizons opened for more effective and accurate processing. This article attempts to use different deep‐learning approaches to detect and segment wetlands on historical Topographic Maps 1: 10000 (TM10), created during the 50s and 60s. Due to the specific symbology of wetlands, their processing can be challenging. It deals with two distinct approaches in the deep learning world, semantic segmentation and object detection, represented by the U‐Net and Single‐Shot Detector (SSD) neural networks, respectively. The suitability, speed, and accuracy of the two approaches in neural networks are analyzed. The results are satisfactory, with the U‐Net F1 score reaching 75.7% and the SSD object detection approach presenting an unconventional alternative.

Digital map processing has been an interest in the image processing and pattern recognition community since the early 80s. With the exponential growth of available map scans in the archives and on the internet, a variety of disciplines in the natural and social sciences grow interests in using historical maps as a primary source of geographical and political information in their studies. Today, many organizations such as the United States Geological Survey, David Rumsey Map Collection, OldMapsOnline.org, and National Library of Scotland, store numerous historical maps in either paper or scanned format. Only a small portion of these historical maps is georeferenced, and even fewer of them have machine-readable content or comprehensive metadata. The lack of a searchable textual content including the spatial and temporal information prevents researchers from efficiently finding relevant maps for their research and using the map content in their studies. These challenges present a tremendous collaboration opportunity for the image processing and pattern recognition community to build advance map processing technologies for transforming the natural and social science studies that use historical maps. This paper presents the potentials of using historical maps in scientific research, describes the current trends and challenges in extracting and recognizing text content from historical maps, and discusses the future outlook.

Weak evidence of long-term extinction debt in Pannonian dry sand grasslands

Disappeared streams are streams that have been buried, removed, or moved as part of the urbanization process. We identified disappeared streams in the Portland, Oregon metropolitan area using historical topographic maps for four time periods, and related them to the history of urban development. The historical maps were used to identify streams visible in older maps but not shown in a more recent version. From 1852 to 1895, 15% of streams disappeared, but the majority of streams disappeared between 1896 and 1953 (65%). This trend continued mainly in suburban areas after 1954 with 12% of streams being removed from 1954 to 1989 and 8% from 1990 to 2017. Stream disappearance can be linked to residential development and prior conversion of land for agriculture depending on the area and time period. Mapping disappeared streams can help urban spatial planners identify where stream daylighting or restoration could be targeted.

Old urban reform usually reactivates the urban fabric in a new era of sustainable development. However, what remains of the former fabric and how it interacts with the new one often inspires curiosity. How the old residents adapt their lives to the new layout should be explored qualitatively and quantitatively. This research aimed to assess the old and new fabrics in the downtown area of Keelung, Taiwan, by considering the interactions between truncated layout, proportion, and infill orientation in the mature and immature interfaces. According to the historical reform map made in 1907, the newly constructed area occupied the old constructed area in seven downtown blocks. On average, the area composed of new buildings ranged from 135.60% to 239.20% of the old area, and the average volume of the buildings reached a maximum of 41.72 m when compared to the old buildings in place prior to the reform. It seems that the new fabric purposefully maintained the old temples at the centers of the blocks. However, the old alleys, which still remain within these blocks, have been significantly overloaded with services and have become auxiliary utility spaces for the in-block residences. With regard to the part of the fabric that was truncated or reoriented by new streets, the modification could also be easily found on the second skin. A physical model analysis used a UAV 3D cloud model and QGIS® to verify the axes, hierarchies, entrances, open spaces, and corners in the commission store block and temple blocks. We found that the 3D point model and historical maps presented a convincing explanation of the evolved fabric from the past to the present. The stepwise segmentation visualizes the enclosed block inside a block on the historical maps and according to the present sections. We found that new roles for old alleys have evolved behind the new fabric.

Historical enclosure era property-related maps can tell us a great deal about the life and times of communities in the past. This study offers a unique approach to studying the historical landscape by applying GIS techniques to the examination of an eighteenth-century English village. Using novel GIS applications relying on historical maps, the study explores various aspects of the village’s physical and social characteristics. In doing so, the study forges effective linkages between cultural and landscape variables to reveal aspects of the historical landscape in eighteenth-century Britain previously inaccessible to researchers. This, in turn, provides a much more comprehensive and sophisticated template for future use by historical geographers in a number of contexts.

Historical maps are valuable sources of geospatial data for various geography-related applications, providing insightful information about historical land use, transportation infrastructure, and settlements. While transformer-based segmentation methods have been widely applied to image segmentation tasks, they have mostly focused on satellite images. There is a growing need to explore transformer-based approaches for geospatial object extraction from historical maps, given their superior performance over traditional convolutional neural network (CNN)-based architectures. In this research, we aim to automatically extract five different road types from historical maps, using a road dataset digitized from the scanned Deutsche Heereskarte 1:200,000 Türkei (DHK 200 Turkey) maps. We applied the variants of the transformer-based SegFormer model and evaluated the effects of different encoders, batch sizes, loss functions, optimizers, and augmentation techniques on road extraction performance. Our best results, with an intersection over union (IoU) of 0.5411 and an F1 score of 0.7017, were achieved using the SegFormer-B2 model, the Adam optimizer, and the focal loss function. All SegFormer-based experiments outperformed previously reported CNN-based segmentation models on the same dataset. In general, increasing the batch size and using larger SegFormer variants (from B0 to B2) resulted in improved accuracy metrics. Additionally, the choice of augmentation techniques significantly influenced the outcomes. Our results demonstrate that SegFormer models substantially enhance true positive predictions and resulted in higher precision metric values. These findings suggest that the output weights could be directly applied to transfer learning for similar historical maps and the inference of additional DHK maps, while offering a promising architecture for future road extraction studies.

Comparing historical map images of the same region from different periods is an effective method for studying urban history and planning. Image registration techniques in the field of computer vision can be applied to this task. However, historical map registration faces unique challenges, including insufficient training data, variations in image sizes, and unavailable texture features. To address these challenges, we constructed a dedicated dataset of over 100 scanned historical maps, including both raw and preprocessed segmented images. We then developed an enhanced SuperGlue-based registration framework, optimized for the specific obstacles posed by historical maps, such as low texture and large image size. Additionally, we proposed a self-supervised fine-tuning feature extraction algorithm and a Transformer-based architecture utilizing graph attention mechanisms to refine feature descriptors and enhance feature matching performance. Experimental results indicate that our solution achieves superior performance compared to existing models, with RMSE reduced by up to 20%, ROCC improved by up to 10%, and processing time shortened by at least 15%.

The research on the historical production areas of Dao-di herbs is of great value to the quality evaluation, production base and protection for geographic indications of Dao-di herbs. Current studies mostly focused on the sorting of written sources, but neglected the excavation of image records such as historical maps and topographic maps. This paper aims at exploreing the geographical scope and evolution mode of historical production area of the Dao-di herbs by combining the method of historical map labelling with the traditional literature and historical research methods. It can be divided into three steps: production area name extraction, historical map labelling and textual research on the historical production area of Dao-di herbs. This method may provide a better way to show the geographical scope and topographic features of the historical production areas of Dao-di herbs through historical maps labelling, which is essential to further explore the evolution of production areas of Dao-di herbs from ancient times to the present by comparing historical maps of different periods, and may be helpful to discover the reasons for the formation and evolution of historical producing areas of Dao-di herbs from different perspectives such as environment, climate, humanities, economy, policy, etc. In addition, the historical map database can be used for map labelling to help establish the relationship between the dynasties, historical names, and change cha-racteristics of the scope of the historical production areas of Dao-di herbs in the following research.

Genfundne gravhøje i Nordjylland – Kartografiske studier

The fluvial dynamics of the Danube in the Mohács Island region (Southern Hungary) were analyzed using historical maps spanning the last 500 years. Battle of Mohács, the defeat of the Hungarian armies by the Ottoman Empire took place here in 1526, in environmental conditions that are quite different from today. To reconstruct these conditions, the behaviour of the Danube, the main influencing factor has been studied.Numerous historical maps, like Tabula Hungariae (1528), Marsigli’s (1726), Müller’s (1709), Lipszky’s (1803) and Korabinszky’s (1804) maps together with the three Military Surveys of the Habsburg Empire (1782-1887) have been transformed or georeferenced and integrated in QGIS for analysis. River branches have been digitized and compared to the present-day situation represented in satellite imagery and a digital elevation model.Apart from comparing the channels of different centuries, sinuosity values of the river branches and oxbow lakes were calculated. The results provide insights into the river's meandering behaviour and its environmental evolution. Although meandering is the dominant in this section, historical evidence indicates a period when the Danube exhibited an island-building phase. During this time, unlike today, the eastern branch of the river marked the main channel, shaping the floodplain. Quantitative analyses demonstrated a general declining trend in sinuosity due to the narrowing of bends, river self-regulation, and recently, human-induced interventions such as river regulation. The persistence of island-building period was likely linked to variations in sediment yield and flow patterns. Historical maps suggest that inflowing streams may have had more discharge during this period, contributing to higher sediment deposition at reduced velocities, particularly when the eastern branch served as the main channel. The eventual reversal of the main branch is attributed to flooding events that redefined the fluvial network. To ensure the reliability of the reconstructions, the accuracy of old maps was also evaluated. The oldest maps depicted rather the character of the river branches, but advances in cartography significantly reduced distortions, enabling the reconstruction of former river courses with greater precision. Comparisons with contemporaneous maps and topographical models highlighted minor deviations and resulted in revision of a few former interpretations. The study also identified key areas where flooding or marshland characteristics could have influenced land use and military strategies, underscoring the broader implications of environmental history in shaping the region's past. This work highlights the critical role of historical cartography and environmental analysis in understanding long-term fluvial transformations and their socio-environmental impacts.

China has undergone a tremendous urbanization process over the past four decades, resulting in a considerable conflict between the desire to construct contemporary urban areas and the desire to safeguard old urban structures. In addition to destroying the physical space of ancient urban sites, urban development has fragmented the natural landscape and severed its structural relationship with the historical urban landscape. In this study, we selected Luoyang as the research object and digitally translated and laminated the laminar process of Luoyang’s historical urban landscape based on historical maps and related historical documents. It is intended to establish a digital historical urban landscape information database comprising data from different periods of the city through the systematic translation of historic maps and through combining the following different landscape carriers: urban spatial patterns, roads and streets, landscape units, and landmark buildings. While reading the historical maps of the city, the spatial analysis tool, ArcGIS, was used to identify the trajectory of the spatial evolution of Luoyang’s spatial structure throughout its history. In this paper, we suggest the establishment of a Luoyang urban historical axis system to integrate the city’s fragmented historical urban landscape, thereby strengthening the social perception of such historical urban landscapes and preserving their memory.

Freemen and villeinsA longue durée perspective on villages, farmsteads and social structure in western Jutland
 Over the course of the last two decades, Danish archaeology has seen a vast increase in excavation activity supported by the introduction of GIS-based systems. Moreover, the digital revolution has made accessible an extensive collection of historical maps, thereby enabling direct comparisons between excavated structures and depictions of the landscape extending back to the late 18th century. The time-consuming process of building complete GIS-systems that include older excavations and reconstructing past landscapes from old maps is ongoing at most Danish museums. This has led to many intriguing correlations and insights. The current models for the settlement history in Denmark during the Iron Age and the Viking period are, however, still primarily based on the findings from the renowned Vorbasse excavations undertaken between 1974 and 1987, and only overviews of these results have been so far published. This article is based on finds and evidence held at the Museum of Southwest Jutland and focuses on western Jutland. With a foundation in excavation results and landscape models extracted from the historical maps of c. 1800, the aim is to apply a longue durée perspective in the search for the underlying structures constituting the agrarian landscape during the last two millennia.The shifting climate appears to have had a profound impact, but written sources like the church list from Ribe diocese of c. AD 1325 give vital clues, which can be compared with the data emerging from the booming research into palaeo-climatic change (figs. 1-4).Danish landscape laws written down in the 13th century distinguish between two types of agrarian settlement: the main village (adelby) and the thorp (torp). Thorps derived from main villages and were in some way subordinate to them. It is argued that this division may extend far back in the Iron Age, and a mapping of main villages has been attempted (figs. 5-7). Analysis of historical maps has shown that the arable areas cultivated in c. 1800 lie where the predecessors of the existing villages are to be found, extending all the way back to the Late Pre-Roman Iron Age. Finds recovered during metal-detector surveys are also found concentrated on this arable land. This indicates a direct continuity in the overall settlement pattern, the associated field systems and the growing community.Based on cases from western Jutland, the settlement structure during the Iron Age and the Viking period is discussed. The excavated villages and farmsteads, their associated cemeteries and the numerous finds recovered by metal detector portray a society based on family-run farmsteads apparently without major class differences – very closely resembling the landscape depicted on historical maps 1000 years later (figs. 8-14). Aristocratic sites or “central places” are also present in this area of southern Scandinavia, but they are few and far between. The second part of the text deals with Medieval (in Denmark c. 1050-1550) villages and farmsteads. Based on excavated examples, it is argued that these are not yet as well understood as their predecessors since large parts of the Medieval remains are hidden underneath existing villages. The structural similarities between the Iron Age villages and their Early Modern counterparts portrayed on the historical maps indicate, however, that Medieval villages also followed the same overall trajectory (figs. 15-27). The conclusion from the analysis is that village formation in western Jutland took place in the Late Pre-Roman Iron Age. Climate- and disease-related events, like the volcanic dust cloud after AD 536 and the Black Death in 1350, appear to be traceable as hiatuses in the archaeological record, but the overall trend is one of continuity. Every village that existed around 1800 seems to have had predecessors going all the way back to the Iron Age. The number of farms in an individual village also seems to have been roughly the same through the ages, indicating that shared ideas about sustainability may, in one form or another, have determined this.