Detection of Apple Trees in Orchard Using Monocular Camera

This study proposes an object detector for apple trees as a first step in developing agricultural digital twins. An original dataset of orchard images was created and used to train Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) models. Performance was evaluated using mean Average...

Full description

Saved in:
Bibliographic Details
Main Authors: Stephanie Nix, Airi Sato, Hirokazu Madokoro, Satoshi Yamamoto, Yo Nishimura, Kazuhito Sato
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/5/564
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050902430318592
author Stephanie Nix
Airi Sato
Hirokazu Madokoro
Satoshi Yamamoto
Yo Nishimura
Kazuhito Sato
author_facet Stephanie Nix
Airi Sato
Hirokazu Madokoro
Satoshi Yamamoto
Yo Nishimura
Kazuhito Sato
author_sort Stephanie Nix
collection DOAJ
description This study proposes an object detector for apple trees as a first step in developing agricultural digital twins. An original dataset of orchard images was created and used to train Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) models. Performance was evaluated using mean Average Precision (mAP). YOLO significantly outperformed SSD, achieving 91.3% mAP compared to the SSD’s 46.7%. Results indicate YOLO’s Darknet-53 backbone extracts more complex features suited to tree detection. This work demonstrates the potential of deep learning for automated data collection in smart farming applications.
format Article
id doaj-art-522e51c71d2c41f8874cd9f3f11010e1
institution DOAJ
issn 2077-0472
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-522e51c71d2c41f8874cd9f3f11010e12025-08-20T02:53:19ZengMDPI AGAgriculture2077-04722025-03-0115556410.3390/agriculture15050564Detection of Apple Trees in Orchard Using Monocular CameraStephanie Nix0Airi Sato1Hirokazu Madokoro2Satoshi Yamamoto3Yo Nishimura4Kazuhito Sato5Faculty of Software and Information Science, Iwate Prefectural University, Takizawa 020-0693, JapanFaculty of Systems Science and Technology, Akita Prefectural University, Yurihonjo 015-0055, JapanFaculty of Software and Information Science, Iwate Prefectural University, Takizawa 020-0693, JapanFaculty of Bioresource Sciences, Akita Prefectural University, Akita 010-0195, JapanAgri-Innovation Education and Research Center, Akita Prefectural University, Ogata 010-0451, JapanFaculty of Systems Science and Technology, Akita Prefectural University, Yurihonjo 015-0055, JapanThis study proposes an object detector for apple trees as a first step in developing agricultural digital twins. An original dataset of orchard images was created and used to train Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) models. Performance was evaluated using mean Average Precision (mAP). YOLO significantly outperformed SSD, achieving 91.3% mAP compared to the SSD’s 46.7%. Results indicate YOLO’s Darknet-53 backbone extracts more complex features suited to tree detection. This work demonstrates the potential of deep learning for automated data collection in smart farming applications.https://www.mdpi.com/2077-0472/15/5/564smart farmingSingle Shot MultiBox DetectorYou Only Look Onceconvolutional neural networkdigital twin
spellingShingle Stephanie Nix
Airi Sato
Hirokazu Madokoro
Satoshi Yamamoto
Yo Nishimura
Kazuhito Sato
Detection of Apple Trees in Orchard Using Monocular Camera
Agriculture
smart farming
Single Shot MultiBox Detector
You Only Look Once
convolutional neural network
digital twin
title Detection of Apple Trees in Orchard Using Monocular Camera
title_full Detection of Apple Trees in Orchard Using Monocular Camera
title_fullStr Detection of Apple Trees in Orchard Using Monocular Camera
title_full_unstemmed Detection of Apple Trees in Orchard Using Monocular Camera
title_short Detection of Apple Trees in Orchard Using Monocular Camera
title_sort detection of apple trees in orchard using monocular camera
topic smart farming
Single Shot MultiBox Detector
You Only Look Once
convolutional neural network
digital twin
url https://www.mdpi.com/2077-0472/15/5/564
work_keys_str_mv AT stephanienix detectionofappletreesinorchardusingmonocularcamera
AT airisato detectionofappletreesinorchardusingmonocularcamera
AT hirokazumadokoro detectionofappletreesinorchardusingmonocularcamera
AT satoshiyamamoto detectionofappletreesinorchardusingmonocularcamera
AT yonishimura detectionofappletreesinorchardusingmonocularcamera
AT kazuhitosato detectionofappletreesinorchardusingmonocularcamera