Primjena računalnog vida za detekciju korova na plantaži jagoda

master's thesis

• Title (english): Application of computer vision for weed detection on strawberry plantation
• Author: Josip Makarun
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2024-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering; Production Mechanical Engineering

Abstract

Razvojem umjetne inteligencije pojavile su se nove tehnologije koje koriste istu. Jedna od njih je i računalni vid koji ima istu ulogu za računala kao što oči imaju kod čovjeka. Uz pomoć računalnog vida mnogi problemi koje je čovjek teško rješavao postaju rješivi od strane računala u veoma kratkom vremenu i to s točnošću kakvom niti jedno ljudsko oko ne može riješiti. U ovome radu uz pomoć YOLOv8 algoritma, trenirat će se model koji će moći detektirati 4 vrste korova na plantaži jagoda. U radu će biti opisan postupak izrade samog modela te bit će dana rješenja za moguća poboljšanja modela u budućnosti.

Abstract (english)

With the development of artificial intelligence, new technologies have appeared that use it. One of them is computer vision, which has the same role for computers as the eyes have for humans. With the help of computer vision, many problems that were difficult for humans to solve became solvable by computers in a very short time and with accuracy that no human eye can solve. In this work, using the YOLOv8 algorithm, a model will be trained to detect 4 types of weed on a strawberry plantation. The process of creating a model will be explained and solutions for possible improvements in the future will be provided.

• Keywords: umjetna inteligencija; duboko učenje; konvolucijske neuronske mreže; računalni vid; prepoznavanje objekata; YOLOv8
• Keywords (english): artificial intelligence; deep learning; convolutional neural networks; computer vision; object recognition; YOLOv8
• Language: croatian
• URN:NBN: urn:nbn:hr:235:461425
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-07-12 16:49:54