Development of Monitoring Robot System for Tomato Fruits in Hydroponic Greenhouses

Crop monitoring is highly important in terms of the efficient and stable performance of tasks such as planting, spraying, and harvesting, and for this reason, several studies are being conducted to develop and improve crop monitoring robots. In addition, the applications of deep learning algorithms...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Dasom Seo, Byeong-Hyo Cho, Kyoung-Chul Kim
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
S
Acceso en línea:https://doaj.org/article/d518360db5c0486da3eb63dd32e2bd5b
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:d518360db5c0486da3eb63dd32e2bd5b
record_format dspace
spelling oai:doaj.org-article:d518360db5c0486da3eb63dd32e2bd5b2021-11-25T16:06:57ZDevelopment of Monitoring Robot System for Tomato Fruits in Hydroponic Greenhouses10.3390/agronomy111122112073-4395https://doaj.org/article/d518360db5c0486da3eb63dd32e2bd5b2021-10-01T00:00:00Zhttps://www.mdpi.com/2073-4395/11/11/2211https://doaj.org/toc/2073-4395Crop monitoring is highly important in terms of the efficient and stable performance of tasks such as planting, spraying, and harvesting, and for this reason, several studies are being conducted to develop and improve crop monitoring robots. In addition, the applications of deep learning algorithms are increasing in the development of agricultural robots since deep learning algorithms that use convolutional neural networks have been proven to show outstanding performance in image classification, segmentation, and object detection. However, most of these applications are focused on the development of harvesting robots, and thus, there are only a few studies that improve and develop monitoring robots through the use of deep learning. For this reason, we aimed to develop a real-time robot monitoring system for the generative growth of tomatoes. The presented method detects tomato fruits grown in hydroponic greenhouses using the Faster R-CNN (region-based convolutional neural network). In addition, we sought to select a color model that was robust to external light, and we used hue values to develop an image-based maturity standard for tomato fruits; furthermore, the developed maturity standard was verified through comparison with expert classification. Finally, the number of tomatoes was counted using a centroid-based tracking algorithm. We trained the detection model using an open dataset and tested the whole system in real-time in a hydroponic greenhouse. A total of 53 tomato fruits were used to verify the developed system, and the developed system achieved 88.6% detection accuracy when completely obscured fruits not captured by the camera were included. When excluding obscured fruits, the system’s accuracy was 90.2%. For the maturity classification, we conducted qualitative evaluations with the assistance of experts.Dasom SeoByeong-Hyo ChoKyoung-Chul KimMDPI AGarticledeep learninghydroponic greenhousematurity levelsmonitoring robotobject detectionAgricultureSENAgronomy, Vol 11, Iss 2211, p 2211 (2021)
institution DOAJ
collection DOAJ
language EN
topic deep learning
hydroponic greenhouse
maturity levels
monitoring robot
object detection
Agriculture
S
spellingShingle deep learning
hydroponic greenhouse
maturity levels
monitoring robot
object detection
Agriculture
S
Dasom Seo
Byeong-Hyo Cho
Kyoung-Chul Kim
Development of Monitoring Robot System for Tomato Fruits in Hydroponic Greenhouses
description Crop monitoring is highly important in terms of the efficient and stable performance of tasks such as planting, spraying, and harvesting, and for this reason, several studies are being conducted to develop and improve crop monitoring robots. In addition, the applications of deep learning algorithms are increasing in the development of agricultural robots since deep learning algorithms that use convolutional neural networks have been proven to show outstanding performance in image classification, segmentation, and object detection. However, most of these applications are focused on the development of harvesting robots, and thus, there are only a few studies that improve and develop monitoring robots through the use of deep learning. For this reason, we aimed to develop a real-time robot monitoring system for the generative growth of tomatoes. The presented method detects tomato fruits grown in hydroponic greenhouses using the Faster R-CNN (region-based convolutional neural network). In addition, we sought to select a color model that was robust to external light, and we used hue values to develop an image-based maturity standard for tomato fruits; furthermore, the developed maturity standard was verified through comparison with expert classification. Finally, the number of tomatoes was counted using a centroid-based tracking algorithm. We trained the detection model using an open dataset and tested the whole system in real-time in a hydroponic greenhouse. A total of 53 tomato fruits were used to verify the developed system, and the developed system achieved 88.6% detection accuracy when completely obscured fruits not captured by the camera were included. When excluding obscured fruits, the system’s accuracy was 90.2%. For the maturity classification, we conducted qualitative evaluations with the assistance of experts.
format article
author Dasom Seo
Byeong-Hyo Cho
Kyoung-Chul Kim
author_facet Dasom Seo
Byeong-Hyo Cho
Kyoung-Chul Kim
author_sort Dasom Seo
title Development of Monitoring Robot System for Tomato Fruits in Hydroponic Greenhouses
title_short Development of Monitoring Robot System for Tomato Fruits in Hydroponic Greenhouses
title_full Development of Monitoring Robot System for Tomato Fruits in Hydroponic Greenhouses
title_fullStr Development of Monitoring Robot System for Tomato Fruits in Hydroponic Greenhouses
title_full_unstemmed Development of Monitoring Robot System for Tomato Fruits in Hydroponic Greenhouses
title_sort development of monitoring robot system for tomato fruits in hydroponic greenhouses
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/d518360db5c0486da3eb63dd32e2bd5b
work_keys_str_mv AT dasomseo developmentofmonitoringrobotsystemfortomatofruitsinhydroponicgreenhouses
AT byeonghyocho developmentofmonitoringrobotsystemfortomatofruitsinhydroponicgreenhouses
AT kyoungchulkim developmentofmonitoringrobotsystemfortomatofruitsinhydroponicgreenhouses
_version_ 1718413345065795584