Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images

Brazil is the largest producer of oranges in the world and the automatic detection of fruits has been a challenging task in the context of remote sensing, due to variations in fruit appearance, changes in lighting and occlusions of foliage and neighboring fruits. In this sense, this paper focus on t...

Full description

Saved in:
Bibliographic Details
Main Authors: M. R. Oviedo Espinosa, L. R. Porto, V. S. W. Orlando, A. M. G. Tommaselli, A. P. Dal Poz, N. N. Imai
Format: Article
Language:English
Published: Copernicus Publications 2024-11-01
Series:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-annals.copernicus.org/articles/X-3-2024/303/2024/isprs-annals-X-3-2024-303-2024.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850178743867277312
author M. R. Oviedo Espinosa
L. R. Porto
V. S. W. Orlando
A. M. G. Tommaselli
A. P. Dal Poz
N. N. Imai
author_facet M. R. Oviedo Espinosa
L. R. Porto
V. S. W. Orlando
A. M. G. Tommaselli
A. P. Dal Poz
N. N. Imai
author_sort M. R. Oviedo Espinosa
collection DOAJ
description Brazil is the largest producer of oranges in the world and the automatic detection of fruits has been a challenging task in the context of remote sensing, due to variations in fruit appearance, changes in lighting and occlusions of foliage and neighboring fruits. In this sense, this paper focus on the detection of oranges in multispectral images, with different spectral bands and exposures, using a convolutional neural network (CNN) known as YOU ONLY LOOK ONCE (YOLO). The results indicate that, after 300 epochs, the model demonstrated an accuracy of 81.5% and an approximate recovery rate of 85%. Shutter speeds 1/640s and 1/250s are not suitable for detection due to low light and overexposure, respectively. Intermediate values may be more suitable for identifying a larger number of fruits.
format Article
id doaj-art-577388c2929e44c9a5f75acc76a5b1c3
institution OA Journals
issn 2194-9042
2194-9050
language English
publishDate 2024-11-01
publisher Copernicus Publications
record_format Article
series ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-577388c2929e44c9a5f75acc76a5b1c32025-08-20T02:18:39ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502024-11-01X-3-202430330810.5194/isprs-annals-X-3-2024-303-2024Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure ImagesM. R. Oviedo Espinosa0L. R. Porto1V. S. W. Orlando2A. M. G. Tommaselli3A. P. Dal Poz4N. N. Imai5São Paulo State University (UNESP), Presidente Prudente, São Paulo, BrazilSão Paulo State University (UNESP), Presidente Prudente, São Paulo, BrazilSão Paulo State University (UNESP), Presidente Prudente, São Paulo, BrazilSão Paulo State University (UNESP), Presidente Prudente, São Paulo, BrazilSão Paulo State University (UNESP), Presidente Prudente, São Paulo, BrazilSão Paulo State University (UNESP), Presidente Prudente, São Paulo, BrazilBrazil is the largest producer of oranges in the world and the automatic detection of fruits has been a challenging task in the context of remote sensing, due to variations in fruit appearance, changes in lighting and occlusions of foliage and neighboring fruits. In this sense, this paper focus on the detection of oranges in multispectral images, with different spectral bands and exposures, using a convolutional neural network (CNN) known as YOU ONLY LOOK ONCE (YOLO). The results indicate that, after 300 epochs, the model demonstrated an accuracy of 81.5% and an approximate recovery rate of 85%. Shutter speeds 1/640s and 1/250s are not suitable for detection due to low light and overexposure, respectively. Intermediate values may be more suitable for identifying a larger number of fruits.https://isprs-annals.copernicus.org/articles/X-3-2024/303/2024/isprs-annals-X-3-2024-303-2024.pdf
spellingShingle M. R. Oviedo Espinosa
L. R. Porto
V. S. W. Orlando
A. M. G. Tommaselli
A. P. Dal Poz
N. N. Imai
Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images
title_full Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images
title_fullStr Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images
title_full_unstemmed Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images
title_short Evaluation of YOLO Efficiency in Automatic Orange Detection in Multi-Exposure Images
title_sort evaluation of yolo efficiency in automatic orange detection in multi exposure images
url https://isprs-annals.copernicus.org/articles/X-3-2024/303/2024/isprs-annals-X-3-2024-303-2024.pdf
work_keys_str_mv AT mroviedoespinosa evaluationofyoloefficiencyinautomaticorangedetectioninmultiexposureimages
AT lrporto evaluationofyoloefficiencyinautomaticorangedetectioninmultiexposureimages
AT vsworlando evaluationofyoloefficiencyinautomaticorangedetectioninmultiexposureimages
AT amgtommaselli evaluationofyoloefficiencyinautomaticorangedetectioninmultiexposureimages
AT apdalpoz evaluationofyoloefficiencyinautomaticorangedetectioninmultiexposureimages
AT nnimai evaluationofyoloefficiencyinautomaticorangedetectioninmultiexposureimages