TrackSherd: Towards an automated archaeological surface survey: development of Machine and deep learning-based methods for automated identification and classification of potsherds in subcentimetric drone-acquired imagery

Investigador/s principal/s: Dr. Arnau Garcia Molsosa (ICAC)
Dates: 02/01/2020 - 01/01/2023
Finançament: AGAUR, Beatriu de Pinós - COFUND (2018-BP-00208)

Fieldwork in Sardinia

TrackSherd is a research project aiming to the development of new instruments for the identification, quantification and interpretation of archaeological items found in the surface. Our current approach is based on the development of machine and deep learning based methods for the automated identification and classification of potsherds in subcentimetric drone-acquired imagery.

COMPARTEIX: