Encoding and Simulating the Past. A Machine Learning Approach to the Archaeological Information

Ramazzotti, Marco; Buscema, Massimo; Massini, Giulia; Torre, Francesca Della

doi:10.1109/metroarchaeo43810.2018.9089813

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These metadata can be combined with data from various areas to create machine learning scenarios [45]. Machine learning techniques have also been applied to automatically annotate tangible and intangible heritage, as well as modern theories and methods of archaeological thought [46].…”

Section: Machine Learning and Artificial Intelligencementioning

confidence: 99%

Digital Tools for Data Acquisition and Heritage Management in Archaeology and Their Impact on Archaeological Practices

Moullou,

Vital,

Sylaiou

et al. 2023

Heritage

View full text Add to dashboard Cite

The significance of data acquisition in archaeological practice has consistently held great importance. Over the past few decades, the growing prevalence of digitization in acquiring data has significantly transformed the landscape of archaeological fieldwork, influencing both methodology and interpretation. The integration of digital photogrammetry and laser scanning technologies in archaeology has transformed data acquisition, enabling efficient and precise documentation. However, this digital shift raises concerns about information overload, the potential loss of on-site insights, and the need for suitable data management methods. Over the past 15 years, digital tools like photogrammetry, laser scanning, and unmanned aerial vehicles have advanced cultural heritage documentation. These methods offer detailed 3D models of archaeological sites, artifacts, and monuments, with evolving accessibility and user friendliness. This paper delves into methods for documenting cultural heritage, examining the implications of various approaches on the archaeologist’s workflow and on the field as a whole.

show abstract

Section: Machine Learning and Artificial Intelligencementioning

confidence: 99%