Adam Gabrič
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Adam Gabrič has a total of 89 co-authors. Here are the top co-authors by number of shared publications:
- Žiga Kokalj
Research Centre of the Slovenian Academy of Sciences and Arts (ZRC SAZU), Novi trg 2, 1000 Ljubljana, Slovenia
6 shared publications - Dejan Grigillo
Faculty of Civil and Geodetic Engineering, University of Ljubljana, Jamova cesta 2, 1000 Ljubljana, Slovenia
3 shared publications - Krištof Oštir
Faculty of Civil and Geodetic Engineering, University of Ljubljana, Jamova cesta 2, 1000 Ljubljana, Slovenia
3 shared publications - Alen Mangafić
Geodetic Instiutute of Slovenia, Jamova cesta 2, 1000 Ljubljana, Slovenia
2 shared publications - Aleš Marsetič
Institute of Anthropological and Spatial Studies, Research Center of the Slovenian Academy of Sciences and Arts, Ljubljana, Slovenia
2 shared publications - Ana Potočnik Buhvald
Faculty of Civil and Geodetic Engineering, University of Ljubljana, Jamova cesta 2, 1000 Ljubljana, Slovenia
2 shared publications
Latest Publications
- Open Access
- 30 September 2026
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU)
Vizualizacija morfoloških sprememb obalnih klifov
- 30 September 2026
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU)
Open AccessVizualizacija morfoloških sprememb obalnih klifov
- Open Access
- 30 September 2026
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU)
Pametni prostor
The publication Smart Space is the 18th volume in the GIS in Slovenia series. The book aims to present the many new findings made in recent years by researchers working in the field of geographic information systems in Slovenia. Geoinformation tools and the growing availability of diverse spatial data enable research of a wide range of processes and phenomena, as well as the development of numerous web applications. The book presents project results and research findings in fields such as geomorphology, environmental protection, geography, geodesy, forestry, dialectology, cartography, remote sensing, natural disaster prevention, telecommunications, and others. Readers will discover innovative applications of geographic information systems while also gaining insight into interesting research findings across numerous fields.
- 30 September 2026
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU)
Open AccessPametni prostor
The publication Smart Space is the 18th volume in the GIS in Slovenia series. The book aims to present the many new findings made in recent years by researchers working in the field of geographic information systems in Slovenia. Geoinformation tools and the growing availability of diverse spatial data enable research of a wide range of processes and phenomena, as well as the development of numerous web applications. The book presents project results and research findings in fields such as geomorphology, environmental protection, geography, geodesy, forestry, dialectology, cartography, remote sensing, natural disaster prevention, telecommunications, and others. Readers will discover innovative applications of geographic information systems while also gaining insight into interesting research findings across numerous fields.
- Open Access
- 26 November 2025
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 47 (1) , 97-123
The effect of forest in the training dataset on the detection of woody vegetation landscape features in agricultural land
- 26 November 2025
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 47 (1) , 97-123
Open AccessThe effect of forest in the training dataset on the detection of woody vegetation landscape features in agricultural land
- Open Access
- 26 September 2024
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU)
Digitalne vezi
The publication Digitalne vezi (‘Digital Connections’) is the 17th book in the series ‘GIS v Sloveniji’ [GIS in Slovenia]. Its aim is to present diverse findings of researchers from the world of geographic information systems in Slovenia from recent years. Powerful data acquisition sensors and geoinformation tools enable research of various processes and phenomena, and a number of web-based applications are being developed to display spatial information. The book presents the results of projects and research findings in fields such as geomorphology, environmental protection, geography, geodesy, forestry, transport, tourism, remote sensing, agriculture and others. Readers will find in the book new possibilities for the use of geographic information systems and can find out about interesting research results in a wide range of fields.
- 26 September 2024
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU)
Open AccessDigitalne vezi
The publication Digitalne vezi (‘Digital Connections’) is the 17th book in the series ‘GIS v Sloveniji’ [GIS in Slovenia]. Its aim is to present diverse findings of researchers from the world of geographic information systems in Slovenia from recent years. Powerful data acquisition sensors and geoinformation tools enable research of various processes and phenomena, and a number of web-based applications are being developed to display spatial information. The book presents the results of projects and research findings in fields such as geomorphology, environmental protection, geography, geodesy, forestry, transport, tourism, remote sensing, agriculture and others. Readers will find in the book new possibilities for the use of geographic information systems and can find out about interesting research results in a wide range of fields.
- Open Access
- 26 September 2024
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU)
Effects of position incongruence of remote sensing data on tree classification
- 26 September 2024
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU)
Open AccessEffects of position incongruence of remote sensing data on tree classification
- Open Access
- 1 January 2024
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU) in Geografski vestnik
- Vol. 95 (2) , 113-134
Zaznavanje olesenele vegetacije s konvolucijsko nevronsko mrežo U-Net
S konvolucijsko nevronsko mrežo U-Net smo zaznavali posamezna drevesa, skupine dreves in grmovnic, drevorede, gozd, mejice, obvodno vegetacijo in drevesa v sadovnjakih, ki jih gradijo različne vrste olesenele vegetacije. Osnovni vhodni podatek je bil ortofoto, ki smo mu z namenom boljše klasifikacije dodajali dodatne sloje. Najboljši rezultat smo dobili s kombinacijo ortofota in modela višin krošenj – skupna natančnost klasifikacije je bila 93,3%. Ta kombinacija vhodnih podatkov je zvišala natančnost klasifikacije razredov gozd in ostalo, ki predstavljata daleč največji delež učnih vzorcev, medtem ko je bil rezultat za manj zastopane razrede (zlasti drevored) tudi pri tej klasifikaciji slabši. Woody vegetation detection with the U-Net convolutional neural network Single trees, groups of trees and bushes, trees in rows, forest, hedges, riparian vegetation and trees in orchards, all of which are composed by different woody vegetation species, were classified using convolutional neural network U-Net. National orthophoto represented basic input data, however adding further layers was tested with a view of improving classification. Best results were obtained using orthophoto and canopy height model combination, the overall accuracy reached 93.3%. This combination increased accuracies achieved at two biggest classes (classes forest and other). The model performed much worse with other classes, that were less represented in training data, which is especially true for trees in rows.
- 1 January 2024
- Published by The Research Center of the Slovenian Academy of Sciences and Arts (ZRC SAZU) in Geografski vestnik
- Vol. 95 (2) , 113-134
Open AccessZaznavanje olesenele vegetacije s konvolucijsko nevronsko mrežo U-Net
S konvolucijsko nevronsko mrežo U-Net smo zaznavali posamezna drevesa, skupine dreves in grmovnic, drevorede, gozd, mejice, obvodno vegetacijo in drevesa v sadovnjakih, ki jih gradijo različne vrste olesenele vegetacije. Osnovni vhodni podatek je bil ortofoto, ki smo mu z namenom boljše klasifikacije dodajali dodatne sloje. Najboljši rezultat smo dobili s kombinacijo ortofota in modela višin krošenj – skupna natančnost klasifikacije je bila 93,3%. Ta kombinacija vhodnih podatkov je zvišala natančnost klasifikacije razredov gozd in ostalo, ki predstavljata daleč največji delež učnih vzorcev, medtem ko je bil rezultat za manj zastopane razrede (zlasti drevored) tudi pri tej klasifikaciji slabši. Woody vegetation detection with the U-Net convolutional neural network Single trees, groups of trees and bushes, trees in rows, forest, hedges, riparian vegetation and trees in orchards, all of which are composed by different woody vegetation species, were classified using convolutional neural network U-Net. National orthophoto represented basic input data, however adding further layers was tested with a view of improving classification. Best results were obtained using orthophoto and canopy height model combination, the overall accuracy reached 93.3%. This combination increased accuracies achieved at two biggest classes (classes forest and other). The model performed much worse with other classes, that were less represented in training data, which is especially true for trees in rows.