Using Machine Learning Techniques in the Visual Detection of Starlings in Vineyards

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F21%3APU140866" target="_blank" >RIV/00216305:26220/21:PU140866 - isvavai.cz</a>
Result on the web
<a href="https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2021_sbornik_2.pdf" target="_blank" >https://www.fekt.vut.cz/conf/EEICT/archiv/sborniky/EEICT_2021_sbornik_2.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Using Machine Learning Techniques in the Visual Detection of Starlings in Vineyards
Original language description
This project deals with visual detection of starlings. The aim is to create an early warning de-tection system that protects crops from flocks of starlings. This system uses a computer vi-sion and machine learning algorithms. In the first phase, the activity in the vineyard was col-lected. Further, the neural network model using cloud-based AutoML platform was trained. The final system classifies objects into several categories. These categories include individual birds, flocks and various unintended objects such as flies and bees. Overall, the flock detec-tion algorithm achieved 89% accuracy and 94% sensitivity.
Czech name
—
Czech description
—

Project
<a href="/en/project/TJ04000441" target="_blank" >TJ04000441: A Starling Scaring System Using a Passive Optical Locator</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
EEEICT_2021
ISBN
978-80-214-5943-4
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
102-105
Publisher name
Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií
Place of publication
Brno, Czech Republic
Event location
Brno
Event date
Apr 27, 2021
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)