Search

Your search keyword '"Kokalj, Ziga"' showing total 20 results
Start Over Author "Kokalj, Ziga"
20 results on '"Kokalj, Ziga"'

1. Impact of LiDAR visualisations on semantic segmentation of archaeological objects

Author

Jaturapitpornchai, Raveerat, Poggi, Giulio, Sech, Gregory, Kokalj, Ziga, Fiorucci, Marco, and Traviglia, Arianna

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Deep learning methods in LiDAR-based archaeological research often leverage visualisation techniques derived from Digital Elevation Models to enhance characteristics of archaeological objects present in the images. This paper investigates the impact of visualisations on deep learning performance through a comprehensive testing framework. The study involves the use of eight semantic segmentation models to evaluate seven diverse visualisations across two study areas, encompassing five archaeological classes. Experimental results reveal that the choice of appropriate visualisations can influence performance by up to 8%. Yet, pinpointing one visualisation that outperforms the others in segmenting all archaeological classes proves challenging. The observed performance variation, reaching up to 25% across different model configurations, underscores the importance of thoughtfully selecting model configurations and LiDAR visualisations for successfully segmenting archaeological objects.

Published
2024
Full Text
View/download PDF

2. Transfer Learning of Semantic Segmentation Methods for Identifying Buried Archaeological Structures on LiDAR Data

Author

Sech, Gregory, Soleni, Paolo, der Vaart, Wouter B. Verschoof-van, Kokalj, Žiga, Traviglia, Arianna, and Fiorucci, Marco

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

When applying deep learning to remote sensing data in archaeological research, a notable obstacle is the limited availability of suitable datasets for training models. The application of transfer learning is frequently employed to mitigate this drawback. However, there is still a need to explore its effectiveness when applied across different archaeological datasets. This paper compares the performance of various transfer learning configurations using two semantic segmentation deep neural networks on two LiDAR datasets. The experimental results indicate that transfer learning-based approaches in archaeology can lead to performance improvements, although a systematic enhancement has not yet been observed. We provide specific insights about the validity of such techniques that can serve as a baseline for future works., Comment: Accepted to IEEE International Geoscience and Remote Sensing Symposium 2023 (IGARSS 2023) @IEEE copyright

Published
2023

3. Discover the Mysteries of the Maya: Selected Contributions from the Machine Learning Challenge & The Discovery Challenge Workshop at ECML PKDD 2021

Author

Kocev, Dragi, Simidjievski, Nikola, Kostovska, Ana, Dimitrovski, Ivica, and Kokalj, Žiga

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

The volume contains selected contributions from the Machine Learning Challenge "Discover the Mysteries of the Maya", presented at the Discovery Challenge Track of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021). Remote sensing has greatly accelerated traditional archaeological landscape surveys in the forested regions of the ancient Maya. Typical exploration and discovery attempts, beside focusing on whole ancient cities, focus also on individual buildings and structures. Recently, there have been several successful attempts of utilizing machine learning for identifying ancient Maya settlements. These attempts, while relevant, focus on narrow areas and rely on high-quality aerial laser scanning (ALS) data which covers only a fraction of the region where ancient Maya were once settled. Satellite image data, on the other hand, produced by the European Space Agency's (ESA) Sentinel missions, is abundant and, more importantly, publicly available. The "Discover the Mysteries of the Maya" challenge aimed at locating and identifying ancient Maya architectures (buildings, aguadas, and platforms) by performing integrated image segmentation of different types of satellite imagery (from Sentinel-1 and Sentinel-2) data and ALS (lidar) data., Comment: Chapter authors. Chapter 1: Matthew Painter and Iris Kramer; Chapter 2: J\"urgen Landauer, Burkhard Hoppenstedt, and Johannes Allgaier; Chapter 3: Thorben Hellweg, Stefan Oehmcke, Ankit Kariryaa, Fabian Gieseke, and Christian Igel; Chapter 4: Christian Ayala, Carlos Aranda, and Mikel Galar

Published
2022

8. Crossing Borders: A Multi-Layer GIS Mapping Framework for the Cultural Management of the Mundo Maya Region

Author

Kokalj, Žiga, Pehani, Peter, Goodchild, Helen, Gaffney, Vincent, Oštir, Krištof, Edmonds, Ernest, Editor-in-chief, Nake, Frieder, Series editor, Bryan-Kinns, Nick, Series editor, Candy, Linda, Series editor, England, David, Series editor, Hugill, Andrew, Series editor, Amitani, Shigeki, Series editor, Riecken, Doug, Series editor, Ch'ng, Eugene, editor, Gaffney, Vincent, editor, and Chapman, Henry, editor

Published
2013
Full Text
View/download PDF

12. Application of sky-view factor for the visualisation of historic landscape features in lidar-derived relief models

Author

Kokalj, Ziga, Zaksek, Klemen, and Ostir, Kristof

Subjects
Slovenia -- Natural history, Cartography -- Methods, Optical radar -- Usage, Historic sites -- Protection and preservation -- Research, Anthropology/archeology/folklore
Abstract

Aerial mapping and remote sensing takes another step forward with this method of modelling lidar data. The usual form of presentation, hill shade, uses a point source to show up surface features. Sky-view factor simulates diffuse light by computing how much of the sky is visible from each point. The result is a greatly improved visibility--as shown here by its use on a test site of known topography in Slovenia. Keywords: sky-view factor, relief visualisation, historic landscape, airborne laser scanning, lidar, Introduction Airborne laser scanning (also known as lidar imaging) has provided major advances in remote sensing. Because the technology enables production of digital elevation models of very high resolution (better [...]

Published
2011

13. Airborne lidar and historic environment records

Author

Challis, Keith, Kokalj, Ziga, Kincey, Mark, Moscrop, Derek, and Howard, Andy J.

Subjects
Optical radar -- Usage, Photography, Aerial -- Methods -- Usage, Surveying -- Methods -- Usage, Anthropology/archeology/folklore, Usage, Methods
Abstract

The authors assess the potential contribution of lidar surveys to national inventories of archaeological resources ('Historic Environment Records), and compare the relative costs and sensitivity of lidar and aerial photography. [...]

Published
2008

14. Understanding past territorial dynamics through the integrated study of movement, pathways and transport networks

Author

Nuninger, Laure, Verhagen, Philip, Opitz, Rachel, Vurpillot, Damien, Bertoncello, Frédérique, Čučković, Zoran, Fovet, Elise, Fruchart, Catherine, Kokalj, Ziga, Štular, Benjamin, De Kleijn, Maurice, Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (UAR 3124) (MSHE), Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Centre National de la Recherche Scientifique (CNRS), Laboratoire Chrono-environnement - CNRS - UBFC (UMR 6249) (LCE), Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC), Research Institute for Culture, History and Heritage (CLUE+), Vrije Universiteit Amsterdam [Amsterdam] (VU), Archaeology, School of Humanities, Univ. of Glasgow, University of Glasgow, Culture et Environnements, Préhistoire, Antiquité, Moyen-Age (CEPAM), Université Côte d'Azur (UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA), Institute of Anthropological and Spatial Studies (IAPŠ) (ZRC SAZU), Znanstvenoraziskovalni center SAZU - Institut za arheologijo, Institut za arheologijo (ZRC SAZU), CNRS, Université de Franche-Comté, PICS MoveScape, and Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (MSHE)

Subjects
models, [SHS.STAT]Humanities and Social Sciences/Methods and statistics, [SHS.ARCHEO]Humanities and Social Sciences/Archaeology and Prehistory, territorial dynamics, networks, pathways, [SHS.GEO]Humanities and Social Sciences/Geography, movement, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, [SHS]Humanities and Social Sciences
Abstract

International audience; Settlement patterns and path networks represent different but connected perspectives on human-environment interaction through movement, manifested through the appropriation and organisation of landscape by societies. Settlement patterns and path networks evolve with unharmonized temporalities, but in constant interaction which render the territorial studies very challenging. Remote sensing, GIS and 3D modeling have greatly contributed to our knowledge and understanding of movement as encapsulated in routes, but the methods employed make it difficult to connect with theories of engagement through travel. Pragmatically, it is difficult to integrate LiDAR-detected traces of pathways, which conflate temporalities, with network analysis techniques and settlement pattern analysis which focus on changing patterns over time.This paper argues for an integrated approach. After a general review of the main methods developed to detect and model movement, pathways and networks of transportation, a conceptual framework will be presented that will enable us to make the connection between the material evidence of routes and various computer-based models of movement, and thus better understand territorial dynamics. This conceptual framework investigates connectivity at various spatiotemporal scales. Most importantly, it creates an explicit framework for research using both detection and modelling-led approaches. A comparison of regional case studies from the literature will be presented to discuss the balance between general models and specific contextualisation.

Published
2018

15. Training archaeologists in the use of lidar: the TRAIL experience

Author

Verhagen, Philip, Rodier, Xavier, Nuninger, Laure, Laplaige, Clément, Opitz, Rachel, Kokalj, Ziga, Štular, Benjamin, Research Institute for Culture, History and Heritage (CLUE+), Vrije Universiteit Amsterdam [Amsterdam] (VU), Cités, Territoires, Environnement et Sociétés (CITERES), Centre National de la Recherche Scientifique (CNRS)-Université de Tours (UT), Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (MSHE), Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC), Laboratoire Chrono-environnement - CNRS - UBFC (UMR 6249) (LCE), University of Arkansas [Fayetteville], Institute of Anthropological and Spatial Studies (IAPS), ZRC SAZU, Institut za arheologijo (ZRC SAZU), Znanstvenoraziskovalni center SAZU - Institut za arheologijo, WAC-8 Kyoto Local Organizing Committee Science Council of Japan, Kyoto City Government, ModeLTER, SoLIDAR, European Project: FEDER-ODIT, Université de Tours (UT)-Centre National de la Recherche Scientifique (CNRS), Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (UAR 3124) (MSHE), Laboratoire Chrono-environnement (UMR 6249) (LCE), Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Centre National de la Recherche Scientifique (CNRS), and Centre National de la Recherche Scientifique (CNRS)-Université de Tours

Subjects
[SHS.STAT]Humanities and Social Sciences/Methods and statistics, [SHS.ARCHEO]Humanities and Social Sciences/Archaeology and Prehistory, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [SHS.ENVIR]Humanities and Social Sciences/Environmental studies, ComputingMilieux_MISCELLANEOUS, [SHS]Humanities and Social Sciences
Abstract

International audience

Published
2016

16. La télédétection

Author

Nuninger, Laure, Oštir, Krištof, Kokalj, Ziga, Georges-Leroy, Murielle, Opitz, Rachel, Laboratoire Chrono-environnement - CNRS - UBFC (UMR 6249) (LCE), Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Centre National de la Recherche Scientifique (CNRS), Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (MSHE), Institute of Anthropological and Spatial Studies (IAPS), ZRC SAZU, Laboratoire européen de modélisation des paysages et des territoires dans la longue durée (LEA ModelTER), ZRC SAZU-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC), Direction régionale des affaires culturelles de Lorraine (DRAC de Lorraine), Ministère de la Culture et de la Communication (MCC), Réseau ISA LEA franco-slovène ModeLTER (CNRS/ZRC SAZU/Université de Franche-Comté/Université de Bourgogne) PHC Proteus (MAE) Développement de ressources à haute résolution spatio-temporelle pour la modélisation en archéologie spatiale, Rodier Xavier (dir.), Barge Olivier, Saligny Laure, Nuninger Laure, and Bertoncello Frédérique

Subjects
[SHS.ARCHEO]Humanities and Social Sciences/Archaeology and Prehistory, archéologie, télédétection, remote-sensing, archaeology, GIS, SIG, lidar, image processing, traitement d'image
Abstract

Qu'est-ce que le télédétection ? Un peu de physique... Classification d'image Télédétection et topographie Une approche interdisciplinaire Bibliographie : Pour en savoir plus Etudes de cas

Published
2011

17. La télédétection

Author

Nuninger , Laure, Oštir , Krištof, Kokalj , Ziga, Georges-Leroy , Murielle, Opitz , Rachel, Laboratoire Chrono-environnement ( LCE ), Université Bourgogne Franche-Comté ( UBFC ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Franche-Comté ( UFC ), Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux ( MSHE ), Centre National de la Recherche Scientifique ( CNRS ) -Université de Franche-Comté ( UFC ), Institute of Anthropological and Spatial Studies ( IAPS ), ZRC SAZU, LEA ModeLTER, Centre National de la Recherche Scientifique ( CNRS ), Direction régionale des affaires culturelles de Lorraine ( DRAC de Lorraine ), Ministère de la Culture et de la Communication ( MCC ), Réseau ISA LEA franco-slovène ModeLTER (CNRS/ZRC SAZU/Université de Franche-Comté/Université de Bourgogne) PHC Proteus (MAE) Développement de ressources à haute résolution spatio-temporelle pour la modélisation en archéologie spatiale, and Rodier Xavier (dir.), Barge Olivier, Saligny Laure, Nuninger Laure, Bertoncello Frédérique

Subjects
archéologie, [ SHS.ARCHEO ] Humanities and Social Sciences/Archaeology and Prehistory, télédétection, remote-sensing, archaeology, GIS, SIG, lidar, image processing, traitement d'image
Abstract

Qu'est-ce que le télédétection ? Un peu de physique... Classification d'image Télédétection et topographie Une approche interdisciplinaire Bibliographie : Pour en savoir plus Etudes de cas

Published
2011

18. Confidence maps: a tool to evaluate data's relevance in spatial analysis

Author

Oštir , Krištof, Kokalj , Ziga, Nuninger , Laure, Institute of Anthropological and Spatial Studies (IAPS), ZRC SAZU, Laboratoire européen de modélisation des paysages et des territoires dans la longue durée (LEA ModelTER), Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-ZRC SAZU, Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (UAR 3124) (MSHE), Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Centre National de la Recherche Scientifique (CNRS), Laboratoire Chrono-environnement - CNRS - UBFC (UMR 6249) (LCE), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC), ZRC SAZU-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (MSHE), Institute of Anthropological and Spatial Studies ( IAPS ), LEA ModeLTER, Centre National de la Recherche Scientifique ( CNRS ), Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux ( MSHE ), Centre National de la Recherche Scientifique ( CNRS ) -Université de Franche-Comté ( UFC ), Laboratoire Chrono-environnement ( LCE ), and Université Bourgogne Franche-Comté ( UBFC ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Franche-Comté ( UFC )

Subjects
spatial analysis, confidence maps, modelling territorial intelligence, intelligence territoriale, [SHS.GEO]Humanities and Social Sciences/Geography, [ SHS.GEO ] Humanities and Social Sciences/Geography
Abstract

Inventory data used in archaeology are often incomplete and heterogeneous. In the framework of the ArchaeDyn program, a method has been proposed to evaluate heterogeneity in archaeological inventories. The purpose of this work is to create a validation tool to interpret the results. This tool is called a "confidence map" and is produced by combining representation and reliability maps. The first step consists in generating representation maps to describe the clustering of archaeological items. The second step is based on reliability maps. Data providers are asked to define and outline the level of reliability of their data. Finally, representation and reliability layers are combined using map algebra. The resulting maps allow for the comparison and analysis of data confidence

Published
2008

19. Confidence maps: a tool to evaluate archaeological data's relevance in spatial analysis

Author

Oštir , Krištof, Kokalj , Ziga, Saligny , Laure, Tolle , Florian, Nuninger , Laure, Zakšek , Klemen, Pennors , Francoise, Institute of Anthropological and Spatial Studies ( IAPS ), ZRC SAZU, European laboratory for Modelling of Landscapes and Territories over the Long Term ( LEA MODELTER ), ZRC SAZU-Centre National de la Recherche Scientifique ( CNRS ), Maison des Sciences de l'Homme de Dijon ( MSH Dijon (MSHD) ), Centre National de la Recherche Scientifique ( CNRS ) -Université de Bourgogne ( UB ), Théoriser et modéliser pour aménager ( ThéMA ), Université de Bourgogne ( UB ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Franche-Comté ( UFC ), Laboratoire Chrono-environnement ( LCE ), Université Bourgogne Franche-Comté ( UBFC ) -Centre National de la Recherche Scientifique ( CNRS ) -Université de Franche-Comté ( UFC ), Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux ( MSHE ), Centre National de la Recherche Scientifique ( CNRS ) -Université de Franche-Comté ( UFC ), ArchaeDyn I (2005-2007): 'Spatial dynamic of settlement patterns and natural resources: toward a long‑term integrated analysis from Prehistory to the Middle Ages' (Action Concertée Incitative - ACI Spaces and Territories of French Ministry of Research and New Technologies, contract ET28), coordination F. Favory and L. Nuninger., Posluschny A., Lambers K., Herzog I., Nuninger, Laure, Institute of Anthropological and Spatial Studies (IAPS), European laboratory for Modelling of Landscapes and Territories over the Long Term (LEA MODELTER), ZRC SAZU-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC), Maison des Sciences de l'Homme de Dijon (MSH Dijon (MSHD)), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS), Théoriser et modéliser pour aménager (UMR 6049) (ThéMA), Centre National de la Recherche Scientifique (CNRS)-Université de Bourgogne (UB)-Université de Franche-Comté (UFC), Laboratoire Chrono-environnement - CNRS - UBFC (UMR 6249) (LCE), Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (UAR 3124) (MSHE), Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Centre National de la Recherche Scientifique (CNRS), Posluschny A., Lambers K., Herzog I., Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Centre National de la Recherche Scientifique (CNRS)-Université de Bourgogne (UB), and Maison des Sciences de l'Homme et de l'Environnement Claude Nicolas Ledoux (MSHE)

Subjects
reliability, spatial analysis, archéologie, carte de confiance, confidence map, archaeology, fiabilité, analyse spatiale
Abstract

L'article est disponible en ligne sur Virtual Library Propylaeum : http://archiv.ub.uni-heidelberg.de/propylaeumdok/volltexte/2010/551/pdf/08_05_ostir_et_al_confidence.pdf; International audience

Published
2007

20. Application of Internet GIS tools for heritage management. ARKAS case study

Author

Kokalj, Ziga, Pehani, Peter, Hvala, Sneza Tecco, Oštir, Krištof, Scientific Research Centre of the Slovenian Academy of Sciences and Arts (ZRC SAZU), Institute of Anthropological and Spatial Studies (IAPS), ZRC SAZU, European Project, Girardot, Jean-Jacques, and coordination action of the European Network of Territorial Intelligence - FP6 – 2004 – CITIZENS – 5 - INCOMING

Subjects
Territorial Intelligence, [SHS.STAT]Humanities and Social Sciences/Methods and statistics, [SHS.GEO] Humanities and Social Sciences/Geography, heritage management, [SHS.STAT] Humanities and Social Sciences/Methods and statistics, archaeological information system, internet mapping, Intelligence Territoriale, [SHS.GEO]Humanities and Social Sciences/Geography
Abstract

International audience; Geographical information systems are becoming a common tool in applications that involve spatial objects and relations, including heritage management. In the last years the internet technology is moving GIS towards web based applications, simplifying the interaction between users and GIS, and at the same time reducing the ownership and maintenance costs. Archaeology is forced to incorporate the activities of protection, investigation and presentation to new tendencies of contemporary open society. It has to constantly renew and modernize its informational infrastructure with the purpose of more effective cultural heritage management and as an effective base for research. Internet based databases that include mapping capabilities can provide a useful and efficient way of storing and disseminating data and results to the public and researchers. At the Scientific Research Centre of the Slovenian Academy of Sciences and Arts an internet based mapping application for Archaeological Sites and Monuments Records of Slovenia (ARKAS) has been designed and implemented.

Published
2006

Catalog

Books, media, physical & digital resources
See catalog results