Automatic Detection of Archaeological Features from Airborne Laser Scanning Data

Enlarge

As part of the Digital Heritage Research Colloquium, Prof. Dr. Žiga.Kokalj from ZRC SAZU will present a lecture titled “Automatic Detection of Archaeological Features from Airborne Laser Scanning Data.”

Abstract:

This talk seeks to present an archaeological workflow for creating ML models, experiments for classifying and identifying archaeology (buildings, platforms, aguadas) of the ancient Maya, as well as a user-friendly tool for Automatic Detection of Archaeological Features (ADAF). The underlying ML models have been trained on an extensive archive of ALS datasets in Ireland, labelled by experts with three types of archaeological features (enclosures, ringforts, barrows). We have conducted a series of experiments with different visualisation methods and different ML architectures for object detection and semantic segmentation to find the optimal configurations for the software. Visualisations were computed with the Relief Visualization Toolbox (RVT) which is now available as a Python library, as a QGIS plugin, and as raster functions that can be used in ArcGIS Pro and Enterprise.

The lecture takes place on Thursday, 20 November 2025, at 18:00 c.t., in Lecture Hall A119, LMU Main Building, Geschwister-Scholl-Platz 1.

Flyer Download: Prof. Žiga.Kokalj Public Lecture (JPG, 2,399 KB)