Detecting Cerritos: Automatic Identification of Stone Structures Using Multispectral Aerial Imagery in Huarochirí, Peru

Summary

This is an abstract from the "SAA 2025: Individual Abstracts" session, at the 90th annual meeting of the Society for American Archaeology.

The massification of unmanned aerial vehicles (UAVs or drones) and the development of specialized cameras and sensors for industries like agriculture, public safety, power, or fossil fuel have allowed archaeologists to integrate these new technologies into their practice. While the benefits of UAVs in site mapping—including high-resolution aerial imagery, photogrammetric reconstruction, and multi-angle visualization—are well-established, incorporating multispectral UAVs introduces additional capabilities. These include multispectral data acquisition (G/R/RE/NIR), real-time vegetation health assessment, and, most importantly, sub-centimeter resolution imaging. This study presents a preliminary analysis of multispectral UAV imagery obtained from the archaeological site of Cerritos, in Huarochirí, Peru. We created and used a training dataset for structure identification and conducted a supervised classification analysis to evaluate the efficacy of aerial multispectral data in delineating Cerritos' architectural features. The results are juxtaposed with those derived from conventional RGB photography to assess the comparative advantages of multispectral imaging in archaeological site detection and mapping.

This Resource is Part of the Following Collections

• Society for American Archaeology 90th Annual Meeting, Denver, CO (2025)   •
• SAA 2025: Individual Abstracts

Keywords

Record Identifiers

Abstract Id(s): 53218