BEGIN:VCALENDAR
VERSION:2.0
PRODID:oeguf.ac.at
X-PUBLISHED-TTL:P1D
BEGIN:VEVENT
UID:69d0f8462afc1
DTSTART:20260326T180000
SEQUENCE:0
TRANSP:OPAQUE
DTEND:20260326T200000
LOCATION:Hörsaal 7 des Instituts für Urgeschichte und Historische Archäo
 logie 
SUMMARY:From RVT visualisations to automated detection with ADAF
CLASS:PUBLIC
DESCRIPTION:Vortrag auf Einladung der ÖGUF:&nbsp\;The talk brings together
  airborne laser scanning (ALS\, lidar)\, relief visualisation\, and deep l
 earning to identify and classify archaeological features in landscapes. Vi
 sualisation products derived from raster elevation models remain the found
 ation of most archaeological analyses of ALS data. The Relief Visualisatio
 n Toolbox (RVT) was developed to support the visual interpretation of elev
 ation-model datasets through a curated set of methods that have proven eff
 ective for detecting small-scale features\, with default parameters tuned 
 for that purpose. RVT is now available as a Python library\, a QGIS plugin
 \, and as raster functions for ArcGIS Pro and ArcGIS Enterprise\, allowing
  these techniques to be easily computed for both manual and automated inte
 rpretation.\nAn archaeological workflow for building machine-learning mode
 ls will be presented\, alongside experiments covering a range of contexts:
  buildings\, platforms\, and aguadas of the ancient Maya\; enclosures\, ri
 ngforts\, and barrows in Ireland\; and a landscape of barrows in south-eas
 tern Herzegovina. The underlying models are trained on an extensive archiv
 e of ALS datasets labelled by domain experts. A series of experiments comp
 ares visualisation methods and machine-learning architectures for object d
 etection and semantic segmentation\, with the goal of identifying optimal 
 configurations for a practical\, user-friendly tool for Automatic Detectio
 n of Archaeological Features (ADAF).\nZugangsdaten:\nTeilnahme über Zoom\
 nhttps://us06web.zoom.us/j/85934753909?pwd=e2PEboknlVZvFxgiloXsOGTXwa8U1d.
 1\nTeilnahme über den Internet-Browser:\nhttps://zoom.us/join \nMeeting-I
 D: 859 3475 3909\nKenncode: 590203\n
DTSTAMP:20260404T133846Z
END:VEVENT
END:VCALENDAR