Detection of archaeological surface ceramics using very high-resolution remotely sensed data
Date Issued
April 16, 2024
Abstract
This study explores using Artificial Intelligence (AI) to enhance the detection of archaeological features from images taken by Unmanned Aerial Ve-hicles (UAVs). The aim is to complement traditional archaeological survey meth-ods. With the advancement of Remote Sensing (RS), the use of low-altitude sys-tems for documenting archaeological sites has become popular due to cost-effec-tiveness. Additionally, the application of Machine Learning (ML) and Deep Learning (DL) techniques has shown promise in improving the efficiency of ar-chaeological feature detection. However, there are still challenges in accurately interpreting results, especially when methodologies are inadequate. This study addresses the need to detect non-uniformly better-distributed surface ceramics in high-resolution aerial images, a challenge characterized by imbalanced data dis-tribution. The authors propose an innovative AI-driven methodology; the re-search aims to fill a gap in the current literature, improving the precision and reliability of archaeological research through advanced technological ap-proaches. Upon reviewing the overall results alongside the in-situ survey records, it has been determined that using high-resolution UAV imagery combined with automated AI methods is an effective preliminary approach for detecting surface archaeological ceramics.
Funding
This project has received funding from the European Un-ion’s Horizon Europe Framework Programme (HORIZON-WIDERA-2021-ACCESS-03, Twinning Call) under the grant agreement No 101079377 and the UKRI under pro-ject number 10050486. Views and opinions expressed are, however, those of the au-thor(s) only and do not necessarily reflect those of the European Union or the UKRI. Neither the European Union nor the UKRI can be held responsible for them. This paper is a part of the PhD of the first author on the same topic.
File(s)![Thumbnail Image]()
Name
Detection of archaeological surface.pdf
Size
150.72 KB
Format
Adobe PDF
Checksum (MD5)
aefefe969a1a044230d1b5e8717c722a