Deep Learning Based Apples Counting for Yield Forecast Using Proposed Flying Robotic System
Nowadays, Convolution Neural Network (CNN) based deep learning methods are widely used in detecting and classifying fruits from faults, color and size characteristics. In this study, two different neural network model estimators are employed to detect apples using the Single-Shot Multibox Detection...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/13/6171 |
_version_ | 1797590820350590976 |
---|---|
author | Şahin Yıldırım Burak Ulu |
author_facet | Şahin Yıldırım Burak Ulu |
author_sort | Şahin Yıldırım |
collection | DOAJ |
description | Nowadays, Convolution Neural Network (CNN) based deep learning methods are widely used in detecting and classifying fruits from faults, color and size characteristics. In this study, two different neural network model estimators are employed to detect apples using the Single-Shot Multibox Detection (SSD) Mobilenet and Faster Region-CNN (Faster R-CNN) model architectures, with the custom dataset generated from the red apple species. Each neural network model is trained with created dataset using 4000 apple images. With the trained model, apples are detected and counted autonomously using the developed Flying Robotic System (FRS) in a commercially produced apple orchard. In this way, it is aimed that producers make accurate yield forecasts before commercial agreements. In this paper, SSD-Mobilenet and Faster R-CNN architecture models trained with COCO datasets referenced in many studies, and SSD-Mobilenet and Faster R-CNN models trained with a learning rate ranging from 0.015–0.04 using the custom dataset are compared experimentally in terms of performance. In the experiments implemented, it is observed that the accuracy rates of the proposed models increased to the level of 93%. Consequently, it has been observed that the Faster R-CNN model, which is developed, makes extremely successful determinations by lowering the loss value below 0.1. |
first_indexed | 2024-03-11T01:28:53Z |
format | Article |
id | doaj.art-edc62e74890e495fad70c4fb9c6c55db |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T01:28:53Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-edc62e74890e495fad70c4fb9c6c55db2023-11-18T17:31:36ZengMDPI AGSensors1424-82202023-07-012313617110.3390/s23136171Deep Learning Based Apples Counting for Yield Forecast Using Proposed Flying Robotic SystemŞahin Yıldırım0Burak Ulu1Department of Mechatronic Engineering, Erciyes University, Kayseri 38039, TurkeyDepartment of Mechatronic Engineering, Erciyes University, Kayseri 38039, TurkeyNowadays, Convolution Neural Network (CNN) based deep learning methods are widely used in detecting and classifying fruits from faults, color and size characteristics. In this study, two different neural network model estimators are employed to detect apples using the Single-Shot Multibox Detection (SSD) Mobilenet and Faster Region-CNN (Faster R-CNN) model architectures, with the custom dataset generated from the red apple species. Each neural network model is trained with created dataset using 4000 apple images. With the trained model, apples are detected and counted autonomously using the developed Flying Robotic System (FRS) in a commercially produced apple orchard. In this way, it is aimed that producers make accurate yield forecasts before commercial agreements. In this paper, SSD-Mobilenet and Faster R-CNN architecture models trained with COCO datasets referenced in many studies, and SSD-Mobilenet and Faster R-CNN models trained with a learning rate ranging from 0.015–0.04 using the custom dataset are compared experimentally in terms of performance. In the experiments implemented, it is observed that the accuracy rates of the proposed models increased to the level of 93%. Consequently, it has been observed that the Faster R-CNN model, which is developed, makes extremely successful determinations by lowering the loss value below 0.1.https://www.mdpi.com/1424-8220/23/13/6171deep learningagricultural automationaerial roboticsobject detectioncomputer-vision |
spellingShingle | Şahin Yıldırım Burak Ulu Deep Learning Based Apples Counting for Yield Forecast Using Proposed Flying Robotic System Sensors deep learning agricultural automation aerial robotics object detection computer-vision |
title | Deep Learning Based Apples Counting for Yield Forecast Using Proposed Flying Robotic System |
title_full | Deep Learning Based Apples Counting for Yield Forecast Using Proposed Flying Robotic System |
title_fullStr | Deep Learning Based Apples Counting for Yield Forecast Using Proposed Flying Robotic System |
title_full_unstemmed | Deep Learning Based Apples Counting for Yield Forecast Using Proposed Flying Robotic System |
title_short | Deep Learning Based Apples Counting for Yield Forecast Using Proposed Flying Robotic System |
title_sort | deep learning based apples counting for yield forecast using proposed flying robotic system |
topic | deep learning agricultural automation aerial robotics object detection computer-vision |
url | https://www.mdpi.com/1424-8220/23/13/6171 |
work_keys_str_mv | AT sahinyıldırım deeplearningbasedapplescountingforyieldforecastusingproposedflyingroboticsystem AT burakulu deeplearningbasedapplescountingforyieldforecastusingproposedflyingroboticsystem |