This thesis presents methods and datasets to investigate cartographic heritage on a large scale and from a cultural perspective. Heritage institutions worldwide have digitized more than one million maps, and automated techniques now enable large-scale recognition and extraction of map content. Yet these methods have engaged little with the history of cartography, or the view that maps are semantic-symbolic systems, and cultural objects reflecting political and epistemic expectations. This work leverages a diverse corpus of 771,561 map records and 99,715 digitized images aggregated from 38 digital catalogs. After normalization, the dataset includes 236,925 contributors and spans six centuries, from 1492 to 1948. These data make it possible to chart geographic structures and the global chronology of map publication. The spatial focus of cartography is analyzed in relation to political dynamics, evidencing links between Atlantic maritime charting, the triangular trade, and colonial expansion. Further results document the progression of national, domestic focus and the impact of military conflicts on publication volumes. The research introduces semantic segmentation techniques and object detection models for the generic recognition of land classes and cartographic signs, trained on annotated data and synthetic images. The analysis of land classes shows that maps are designed images whose framing and composition emphasize features through centering and semantic symmetries. The study of cartographic figuration encodes 63 M signs and 25 M fragments into a latent visual space, revealing figurative shifts such as the replacement of relief hachures by terrain contours and showing that signs tend to form locally consistent systems. Analyses of collaboration and diffusion highlight the role of legitimacy, larger actors, and major cities in the spread of figurative norms and semiotic cultures.
翻译:本论文提出了从文化视角大规模研究制图遗产的方法与数据集。全球遗产机构已数字化超过一百万幅地图,自动化技术现可实现地图内容的大规模识别与提取。然而,这些方法鲜少结合制图学历史,也未充分关注地图作为语义符号系统以及反映政治与认知期望的文化对象的特性。本研究利用来自38个数字目录的771,561条地图记录与99,715幅数字化图像构成的多样化语料库。经标准化处理后,数据集涵盖236,925名贡献者,时间跨度六个世纪(1492年至1948年)。这些数据使得绘制地理结构与全球地图出版年表成为可能。研究分析了制图学的空间焦点与政治动态的关联,揭示了北大西洋海图绘制、三角贸易与殖民扩张之间的联系。进一步结果记录了国家化与本土化焦点的演进,以及军事冲突对出版量的影响。本研究引入了语义分割技术与目标检测模型,通过标注数据与合成图像训练,实现了土地类别与制图符号的通用识别。对土地类别的分析表明,地图是通过构图与语义对称性突出特征的设计性图像。对制图图形的研究将6300万个符号与2500万个片段编码至潜在视觉空间,揭示了图形演变(如地形等高线取代晕渲法),并表明符号倾向于形成局部一致的系统。对合作与传播的分析凸显了权威性、大型机构与主要城市在图形规范与符号文化传播中的作用。