prikaz prve stranice dokumenta THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE
  Preuzmi
PDF 2.8 MB
Znanstveni rad - Izvorni znanstveni rad
THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE
Poljoprivreda, 28 (2022), 2; 74-80. https://doi.org/10.18047/poljo.28.2.10
Jurišić, Mladen; Radočaj, Dorijan; Plaščak, Ivan; Galić Subašić, Daria; Petrović, Davor

Institucijski repozitorij: Repozitorij Fakulteta agrobiotehničkih znanosti Osijek

Citirajte ovaj rad

Jurišić, M., Radočaj, D., Plaščak, I., Galić Subašić, D. i Petrović, D. (2022). THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE. Poljoprivreda, 28. (2), 74-80. doi: 10.18047/poljo.28.2.10

Jurišić, Mladen, et al. "THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE." Poljoprivreda, vol. 28, br. 2, 2022, str. 74-80. https://doi.org/10.18047/poljo.28.2.10

Jurišić, Mladen, Dorijan Radočaj, Ivan Plaščak, Daria Galić Subašić i Davor Petrović. "THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE." Poljoprivreda 28, br. 2 (2022): 74-80. https://doi.org/10.18047/poljo.28.2.10

Jurišić, M., et al. (2022) 'THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE', Poljoprivreda, 28(2), str. 74-80. doi: 10.18047/poljo.28.2.10

Jurišić M, Radočaj D, Plaščak I, Galić Subašić D, Petrović D. THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE. Poljoprivreda [Internet]. 20.12.2022. [pristupljeno 25.12.2024.];28(2):74-80. doi: 10.18047/poljo.28.2.10

M. Jurišić, D. Radočaj, I. Plaščak, D. Galić Subašić i D. Petrović, "THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE", Poljoprivreda, vol. 28, br. 2, str. 74-80, Prosinac 2022. [Online]. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:151:739593. [Citirano: 25.12.2024.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:151:739593
Podaci o radu
Naslov (engleski)THE EVALUATION OF THE RGB AND MULTISPECTRAL CAMERA ON THE UNMANNED AERIAL VEHICLE (UAV) FOR THE MACHINE LEARNING CLASSIFICATION OF MAIZE
AutorMladen Jurišić
AutorDorijan Radočaj
AutorIvan Plaščak
AutorDaria Galić Subašić
AutorDavor Petrović
Autorova ustanovaSveučilište Josipa Jurja Strossmayera u Osijeku
Fakultet agrobiotehničkih znanosti Osijek
(Zavod za poljoprivrednu tehniku i obnovljive izvore energije)
Znanstveno / umjetničko
područje, polje i grana		BIOTEHNIČKE ZNANOSTI
Poljoprivreda (agronomija)
Poljoprivredna tehnika i tehnologija
Sažetak (engleski)
This study investigated a crop and soil classification applying the Random Forest machine learning algorithm based on the red-green-blue (RGB) and multispectral sensor imaging deploying an unmanned aerial vehicle (UAV). The study area covered two 10 x 10 m subsets of a maize-sown agricultural parcel near Koška. The highest overall accuracy was obtained in the combination of the red edge (RE), near-infrared (NIR), and normalized difference vegetation index (NDVI) in both subsets, with a 99.8% and 91.8% overall accuracy, respectively. The conducted analysis proved that the RGB camera obtained sufficient accuracy and was an acceptable solution to the soil and vegetation classification. Additionally, a multispectral camera and spectral analysis allowed for a more detailed analysis, primarily of the spectrally similar areas. Thus, this procedure represents a basis for both the crop density calculation and weed detection while deploying an unmanned aerial vehicle. To ensure crop classification effectiveness in practical application, it is necessary to further integrate the weed classes in the current vegetation class and separate them into crop and weed classes.
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objaveObjavljen
Vrsta recenzijeRecenziran - domaća recenzija
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov časopisaPoljoprivreda
Brojčani podacivol. 28, br. 2, str. 74-80
p-ISSN1330-7142
e-ISSN1848-8080
DOIhttps://doi.org/10.18047/poljo.28.2.10
URN:NBNurn:nbn:hr:151:739593
Datum objave publikacije2022-12-20
URL dokumentahttps://hrcak.srce.hr/289119
Vrsta resursaTekst
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Zaštićeno autorskim pravom.
Datum i vrijeme pohrane2024-05-08 11:00:48