Comparative Analysis of Popular CNN Based Deep Learning Models for Tree Trunk Detection in Orchards
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F24%3A00381989" target="_blank" >RIV/68407700:21220/24:00381989 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.14311/NNW.2024.34.014" target="_blank" >https://doi.org/10.14311/NNW.2024.34.014</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.14311/NNW.2024.34.014" target="_blank" >10.14311/NNW.2024.34.014</a>
Alternative languages
Result language
angličtina
Original language name
Comparative Analysis of Popular CNN Based Deep Learning Models for Tree Trunk Detection in Orchards
Original language description
This study compares machine vision deep learning models based on convolutional neural networks to detect tree trunks in orchards from camera images, with a primary focus on apple trees. Two distinct datasets are used, one original with apple trees and another publicly available featuring vineyard trunks. Multiple deep learning models are tested and compared in order to evaluate their efficacy in tree trunk detection. Research not only provides insight into the performance of various models but also serves as a valuable benchmark for assessing achievable results in orchard-based machine vision applications. The findings contribute to the fields understanding of tree trunk detection, facilitating advancements in agricultural automation.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/QK21010170" target="_blank" >QK21010170: New orchard concept using technology 4.0</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Neural Network World
ISSN
1210-0552
e-ISSN
2336-4335
Volume of the periodical
34
Issue of the periodical within the volume
5
Country of publishing house
CZ - CZECH REPUBLIC
Number of pages
15
Pages from-to
263-277
UT code for WoS article
001419989000001
EID of the result in the Scopus database
2-s2.0-105000099164