Instance segmentation for automated weeds and crops detection in farmlands

 

Сохранить в:
Библиографические подробности
Авторы: Mora-Fallas, Adán, Goëau, Hervé, Joly, Alexis, Bonnet, Pierre, Mata-Montero, Erick
Формат: artículo original
Статус:Versión publicada
Дата публикации:2020
Описание:Based on recent successful applications of Deep Learning techniques in classification, detection and segmentation of plants, we propose an instance segmentation approach that uses a Mask R-CNN model for weeds and crops detection on farmlands. We evaluated our model performance with the MSCOCO average precision metric, contrasting the use of data augmentation techniques. Results obtained show how the model fits very well in this context, opening new opportunities to automated weed control solutions, at larger scales.
Страна:Portal de Revistas TEC
Институт:Instituto Tecnológico de Costa Rica
Repositorio:Portal de Revistas TEC
Язык:Inglés
OAI Identifier:oai:ojs.pkp.sfu.ca:article/5069
Online-ссылка:https://revistas.tec.ac.cr/index.php/tec_marcha/article/view/5069
Ключевое слово:Deep learning
instance segmentation
computer vision
precision agriculture
biodiversity informatics
weed detection
species identification
Aprendizaje profundo
segmentación de instancias
visión por computadora
agricultura de precisión
bioinformática
detección de malezas
identificación de especies