Home
PDF download
Cite article
Share options
Informations, rights and permissions
Issue image
Vol 17, 2026
Pages: 1149 - 1156
Professional paper
Geodesy Editor: Mladen Amovic
See full issue

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 

Metrics and citations
Abstract views: 1
PDF Downloads: 0
Google scholar: See link
Article content
  1. Abstract
  2. Disclaimer
Published: 01.06.2026. Professional paper Geodesy Editor: Mladen Amovic

AUTOMATED DETECTION OF EARTH PYRAMIDS AT DEVIL’S TOWN USING PHOTOGRAMMETRIC POINT CLOUDS

By
Nenad Brodić Orcid logo ,
Nenad Brodić
Contact Nenad Brodić

Department of Geodesy and Geoinformatics, University of Belgrade - Faculty of Civil Engineering , Belgrade , Serbia

Miloš Marjanović Orcid logo ,
Miloš Marjanović

University of Belgrade - Faculty of Mining and Geology , Belgrade , Serbia

Mileva Samardžić-Petrović Orcid logo ,
Mileva Samardžić-Petrović

Department of Geodesy and Geoinformatics, Faculty of Civil Engineering, University of Belgrade , Belgrade , Serbia

Dragana Đurić Orcid logo
Dragana Đurić

University of Belgrade - Faculty of Mining and Geology , Belgrade , Serbia

Abstract

The Devil’s Town site is a unique geomorphological formation in southern Serbia, comprising over 200 earth structures. This site has been monitored using non-invasive techniques and a high-resolution point cloud was generated through photogrammetric imaging with an Unmanned Aerial Vehicle (UAV). In this study, automatic detection of the earth pyramids was performed using local maxima detection algorithm in order to create a digital inventory across different time epochs, enabling comparisons between past and present conditions of these geomorphological features. The results were compared with an official digital geomorphological inventory produced through manual mapping, achieving an overall accuracy (OA) exceeding 70%.

Funding Statement

This research was supported by the Science Fund of the Republic of Serbia, Grant TF Cl389-YF, Project No. 7515, Project acronym DEMONITOR. The authors thank the management and staff of ''Planinka'' JSC from Kursumlija for providing support for project activities.

The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.