Prepoznava invazivnih polžev z uporabo globokega učenja

diplomsko delo

Kristjan Herodež (Author), Iztok Fister (Mentor), Grega Vrbančič (Co-mentor)

Abstract

Zaključno delo se osredotoča na podvejo umetne inteligence, ki se imenuje strojno učenje. V zaključnem delu predstavljamo uporabo in implementacijo strojnega učenja na različnih področjih. Znotraj zaključnega dela se podrobneje osredotočamo na pametno kmetijstvo, katerega osrednja tematika v tej nalogi je odkrivanje škodljivcev, ki so v našem primeru polži Arion rufus. Kot rešitev problema je predstavljeno globoko učenje oz. uporaba konvolucijskih nevronskih mrež. V ta namen omenimo tudi različne pristope za učenje modelov računalniškega vida. Rešitev smo našli v pristopu YOLO (You only look once) v katerem smo izdelali naš model vida in ga primerjali s podobno študijo.

Keywords

strojno učenje;globoko učenje;pametno kmetijstvo;umetna inteligenca;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2023
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[K. Herodež]
UDC:	004.85(043.2)
COBISS:	171251203
Views:	65
Downloads:	10
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Detection of invasive snails using deep learning
Secondary abstract:	The thesis focuses on a branch of artificial intelligence called machine learning. In it we present the use and implementation of machine learning in various fields. Primary focus is given to the branch of smart agriculture, whose central theme in this assignment is solving the problem of pest detection, which in our case are Arion rufus snails. Deep learning is presented as a solution to the problem using convolutional neural networks. For this purpose, we also mention different approaches for creating models of computer vision. We found a solution in the YOLO (You only look once) approach, in which we created our vision model and compared it with a similar study.
Secondary keywords:	arion rufus;deep learning;smart agriculture;artificial intelligence;
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Informatika in tehnologije komuniciranja
Pages:	1 spletni vir (1 datoteka PDF (IX, 46 f.))
ID:	19860296