Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees

This paper presents a comparative analysis between two state-of-the-art object detection models, DETR and YOLOv8, focusing on their effectiveness in fruit detection for yield prediction in agriculture. The study begins with data acquisition, utilizing images and corresponding annotations to train an...

Full description

Saved in:
Bibliographic Details
Main Authors: Zineb Jrondi, Abdellatif Moussaid, Moulay Youssef Hadi
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Systems and Soft Computing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772941924000322
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054685198647296
author Zineb Jrondi
Abdellatif Moussaid
Moulay Youssef Hadi
author_facet Zineb Jrondi
Abdellatif Moussaid
Moulay Youssef Hadi
author_sort Zineb Jrondi
collection DOAJ
description This paper presents a comparative analysis between two state-of-the-art object detection models, DETR and YOLOv8, focusing on their effectiveness in fruit detection for yield prediction in agriculture. The study begins with data acquisition, utilizing images and corresponding annotations to train and evaluate the models. Our approach employs a data-driven methodology, dividing the dataset into training and testing sets, with rigorous validation to ensure robustness.For DETR, evaluation results demonstrate promising performance across various IoU thresholds, indicating its effectiveness in accurately localizing fruits within bounding boxes. Additionally, YOLOv8 exhibits substantial improvements in detection performance, achieving high precision and recall rates, particularly noteworthy for ''orange'' and ''sweet_orange'' classes. Notably, the model showcases commendable proficiency even in challenging scenarios.In conclusion, both DETR and YOLOv8 offer valuable insights for precision farming, aiding farmers in yield prediction and harvest planning. While DETR demonstrates robustness and efficiency in fruit detection, YOLOv8 excels in high-precision detection, albeit with longer training times. These findings highlight the potential of advanced object detection models in revolutionizing agricultural practices, contributing to enhanced productivity and market equilibrium.
format Article
id doaj-art-6035c76b9ae240ea8d367aee72d06444
institution DOAJ
issn 2772-9419
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Systems and Soft Computing
spelling doaj-art-6035c76b9ae240ea8d367aee72d064442025-08-20T02:52:10ZengElsevierSystems and Soft Computing2772-94192024-12-01620010310.1016/j.sasc.2024.200103Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within treesZineb Jrondi0Abdellatif Moussaid1Moulay Youssef Hadi2Laboratory for Computer Science Research, Faculty of Sciences Ibn Tofail University, Kénitra, MoroccoENSIAS, Mohammed V University in Rabat, Rabat, 10000, Morocco; Corresponding author.Laboratory for Computer Science Research, Faculty of Sciences Ibn Tofail University, Kénitra, MoroccoThis paper presents a comparative analysis between two state-of-the-art object detection models, DETR and YOLOv8, focusing on their effectiveness in fruit detection for yield prediction in agriculture. The study begins with data acquisition, utilizing images and corresponding annotations to train and evaluate the models. Our approach employs a data-driven methodology, dividing the dataset into training and testing sets, with rigorous validation to ensure robustness.For DETR, evaluation results demonstrate promising performance across various IoU thresholds, indicating its effectiveness in accurately localizing fruits within bounding boxes. Additionally, YOLOv8 exhibits substantial improvements in detection performance, achieving high precision and recall rates, particularly noteworthy for ''orange'' and ''sweet_orange'' classes. Notably, the model showcases commendable proficiency even in challenging scenarios.In conclusion, both DETR and YOLOv8 offer valuable insights for precision farming, aiding farmers in yield prediction and harvest planning. While DETR demonstrates robustness and efficiency in fruit detection, YOLOv8 excels in high-precision detection, albeit with longer training times. These findings highlight the potential of advanced object detection models in revolutionizing agricultural practices, contributing to enhanced productivity and market equilibrium.http://www.sciencedirect.com/science/article/pii/S2772941924000322Fruit detectionObject detectionDETRYOLOv8Yield prediction
spellingShingle Zineb Jrondi
Abdellatif Moussaid
Moulay Youssef Hadi
Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees
Systems and Soft Computing
Fruit detection
Object detection
DETR
YOLOv8
Yield prediction
title Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees
title_full Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees
title_fullStr Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees
title_full_unstemmed Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees
title_short Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees
title_sort exploring end to end object detection with transformers versus yolov8 for enhanced citrus fruit detection within trees
topic Fruit detection
Object detection
DETR
YOLOv8
Yield prediction
url http://www.sciencedirect.com/science/article/pii/S2772941924000322
work_keys_str_mv AT zinebjrondi exploringendtoendobjectdetectionwithtransformersversusyolov8forenhancedcitrusfruitdetectionwithintrees
AT abdellatifmoussaid exploringendtoendobjectdetectionwithtransformersversusyolov8forenhancedcitrusfruitdetectionwithintrees
AT moulayyoussefhadi exploringendtoendobjectdetectionwithtransformersversusyolov8forenhancedcitrusfruitdetectionwithintrees