Cargando…
Real-Time Prediction of Growth Characteristics for Individual Fruits Using Deep Learning
Understanding the growth status of fruits can enable precise growth management and improve the product quality. Previous studies have rarely used deep learning to observe changes over time, and manual annotation is required to detect hidden regions of fruit. Thus, additional research is required for...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9459837/ https://www.ncbi.nlm.nih.gov/pubmed/36080935 http://dx.doi.org/10.3390/s22176473 |
_version_ | 1784786604471091200 |
---|---|
author | Hondo, Takaya Kobayashi, Kazuki Aoyagi, Yuya |
author_facet | Hondo, Takaya Kobayashi, Kazuki Aoyagi, Yuya |
author_sort | Hondo, Takaya |
collection | PubMed |
description | Understanding the growth status of fruits can enable precise growth management and improve the product quality. Previous studies have rarely used deep learning to observe changes over time, and manual annotation is required to detect hidden regions of fruit. Thus, additional research is required for automatic annotation and tracking fruit changes over time. We propose a system to record the growth characteristics of individual apples in real time using Mask R-CNN. To accurately detect fruit regions hidden behind leaves and other fruits, we developed a region detection model by automatically generating 3000 composite orchard images using cropped images of leaves and fruits. The effectiveness of the proposed method was verified on a total of 1417 orchard images obtained from the monitoring system, tracking the size of fruits in the images. The mean absolute percentage error between the true value manually annotated from the images and detection value provided by the proposed method was less than 0.079, suggesting that the proposed method could extract fruit sizes in real time with high accuracy. Moreover, each prediction could capture a relative growth curve that closely matched the actual curve after approximately 150 elapsed days, even if a target fruit was partially hidden. |
format | Online Article Text |
id | pubmed-9459837 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-94598372022-09-10 Real-Time Prediction of Growth Characteristics for Individual Fruits Using Deep Learning Hondo, Takaya Kobayashi, Kazuki Aoyagi, Yuya Sensors (Basel) Article Understanding the growth status of fruits can enable precise growth management and improve the product quality. Previous studies have rarely used deep learning to observe changes over time, and manual annotation is required to detect hidden regions of fruit. Thus, additional research is required for automatic annotation and tracking fruit changes over time. We propose a system to record the growth characteristics of individual apples in real time using Mask R-CNN. To accurately detect fruit regions hidden behind leaves and other fruits, we developed a region detection model by automatically generating 3000 composite orchard images using cropped images of leaves and fruits. The effectiveness of the proposed method was verified on a total of 1417 orchard images obtained from the monitoring system, tracking the size of fruits in the images. The mean absolute percentage error between the true value manually annotated from the images and detection value provided by the proposed method was less than 0.079, suggesting that the proposed method could extract fruit sizes in real time with high accuracy. Moreover, each prediction could capture a relative growth curve that closely matched the actual curve after approximately 150 elapsed days, even if a target fruit was partially hidden. MDPI 2022-08-28 /pmc/articles/PMC9459837/ /pubmed/36080935 http://dx.doi.org/10.3390/s22176473 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Hondo, Takaya Kobayashi, Kazuki Aoyagi, Yuya Real-Time Prediction of Growth Characteristics for Individual Fruits Using Deep Learning |
title | Real-Time Prediction of Growth Characteristics for Individual Fruits Using Deep Learning |
title_full | Real-Time Prediction of Growth Characteristics for Individual Fruits Using Deep Learning |
title_fullStr | Real-Time Prediction of Growth Characteristics for Individual Fruits Using Deep Learning |
title_full_unstemmed | Real-Time Prediction of Growth Characteristics for Individual Fruits Using Deep Learning |
title_short | Real-Time Prediction of Growth Characteristics for Individual Fruits Using Deep Learning |
title_sort | real-time prediction of growth characteristics for individual fruits using deep learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9459837/ https://www.ncbi.nlm.nih.gov/pubmed/36080935 http://dx.doi.org/10.3390/s22176473 |
work_keys_str_mv | AT hondotakaya realtimepredictionofgrowthcharacteristicsforindividualfruitsusingdeeplearning AT kobayashikazuki realtimepredictionofgrowthcharacteristicsforindividualfruitsusingdeeplearning AT aoyagiyuya realtimepredictionofgrowthcharacteristicsforindividualfruitsusingdeeplearning |