In the project "ARCHEO 3.0" a Machine Learning (ML) system for automatic contouring of the stratigraphic units of an archaeological excavation has been experimented. In this research, we have applied the same ML algorithm to aerial color photographs that represent very important tools in the study of ancient topography and landscape archaeology. Aerials of the Vulci necropolis, one of the most important cities of ancient Etruria, have been used. These photos, both vertical and oblique, have been chosen because the marks had been studied and analyzed in a recent PhD work in Ancient Topography. In particular, the traditional mapping method has been compared with the results obtained by means of automated ML algorithm. This experiment has demonstrated that the developed ML algorithm can be applied to aerial photographs for the recognition of archaeological traces, with interesting development prospects.
A machine learning approach to aerial photointerpretation and mapping
Cacciari I;Pocobelli G;Siano S
2019
Abstract
In the project "ARCHEO 3.0" a Machine Learning (ML) system for automatic contouring of the stratigraphic units of an archaeological excavation has been experimented. In this research, we have applied the same ML algorithm to aerial color photographs that represent very important tools in the study of ancient topography and landscape archaeology. Aerials of the Vulci necropolis, one of the most important cities of ancient Etruria, have been used. These photos, both vertical and oblique, have been chosen because the marks had been studied and analyzed in a recent PhD work in Ancient Topography. In particular, the traditional mapping method has been compared with the results obtained by means of automated ML algorithm. This experiment has demonstrated that the developed ML algorithm can be applied to aerial photographs for the recognition of archaeological traces, with interesting development prospects.File | Dimensione | Formato | |
---|---|---|---|
prod_436870-doc_198106.pdf
solo utenti autorizzati
Descrizione: A machine learning approach to aerial photointerpretation and mapping
Tipologia:
Versione Editoriale (PDF)
Dimensione
1.75 MB
Formato
Adobe PDF
|
1.75 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.