prikaz prve stranice dokumenta Detekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja
Access restricted to authenticated users
master's thesis
Detekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:692565
Brković, Leonarda
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Brković, L. (2022). Detekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:692565

Brković, Leonarda. "Detekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:692565

Brković, Leonarda. "Detekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:692565

Brković, L. (2022). 'Detekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 11 July 2024, https://urn.nsk.hr/urn:nbn:hr:179:692565

Brković L. Detekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 July 11] Available at: https://urn.nsk.hr/urn:nbn:hr:179:692565

L. Brković, "Detekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:692565

Metadata
TitleDetekcija grana maslina u svrhu rezidbe korištenjem postupaka dubokog učenja
Title (english)Detection of olive branches for pruning using deep learning procedures
AuthorLeonarda Brković
MentorMirjana Bonković (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-21, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Electronics
Abstract
U radu su predstavljene vrste dubokog učenja, s naglaskom na arhitekture neuronskih mreža, te su opisani njihovi nedostaci i prednosti. Više pažnje posvećeno je maskirnim regionalnim konvolucijskim mrežama (MRCNN), te je korištenjem te mreže razrađen i implementiran postupak za detekciju grana maslina za rezidbu. Opisan je postupak prikupljanja i pripreme podataka, način obrade, treniranja, te u konačnici različiti rezultati testiranja. Iz rezultata se zaključuje da se osim samog odabira parametara standardnih za mreže, posebna pažnja mora obratiti i na kvalitetu skupa podataka, odnosno na veličinu podataka, te kvalitetno označavanje.
Abstract (english)
The paper presents types of deep learning, with an emphasis on neural network architectures, and describes their advantages and disadvantages. More attention was paid to masking regional convolutional networks (MRCNN), and using this network, a procedure for detecting olive branches for pruning was developed and implemented. The procedure of data collection and preparation, the method of processing, training, and ultimately the various test results are described. From the results, it is concluded that in addition to the selection of parameters standard for networks, special attention must be paid to the quality of the data set, i.e. to the size of the data, and quality labeling.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:692565
Study programmeTitle: Electronics and Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektronike i računalnog inženjerstva (magistar/magistra inženjer/inženjerka elektronike i računalnog inženjerstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-03-09 11:22:27