Hybrid attention transformer integrated YOLOV8 for fruit ripeness detection

Abstract The complexity of the outdoor orchard environment, especially the changes in light intensity and the shadows generated by fruit clusters, present challenges in the identification and classification of mature fruits. To solve these problems, this paper proposes an innovative fruit recognitio...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianyin Tang, Zhenglin Yu, ChangShun Shao
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-04184-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334493680238592
author Jianyin Tang
Zhenglin Yu
ChangShun Shao
author_facet Jianyin Tang
Zhenglin Yu
ChangShun Shao
author_sort Jianyin Tang
collection DOAJ
description Abstract The complexity of the outdoor orchard environment, especially the changes in light intensity and the shadows generated by fruit clusters, present challenges in the identification and classification of mature fruits. To solve these problems, this paper proposes an innovative fruit recognition model, HAT-YOLOV8, aiming to combine the advantages of Hybrid Attention Transformer (HAT) and YOLOV8 deep learning algorithm. This model improves the ability to capture complex dependencies by integrating the Shuffle Attention (SA) module while maintaining low computational complexity. In addition, during the feature fusion stage, the Hybrid Attention Transformer (HAT) module is integrated into TopDownLayer2 to enhance the capture of long-term dependencies and the recovery of detailed information in the input data. To more accurately evaluate the similarity between the prediction box and the real bounding box, this paper uses the EIoU loss function instead of CIoU, thereby improving detection accuracy and accelerating model convergence. In terms of evaluation, this study was experimented on a dataset containing five fruit varieties, each of which was classified into three different maturity levels. The results show that the HAT-YOLOV8 model improved mAP by 11%, 10.2%, 7.6% and 7.8% on the test set, and the overall mAP reached 88.9% respectively. In addition, the HAT-YOLOV8 model demonstrates excellent generalization capabilities, indicating its potential for application in the fields of fruit recognition, maturity assessment and fruit picking automation.
format Article
id doaj-art-ec38a675852a4067b3de45f2d404f5aa
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ec38a675852a4067b3de45f2d404f5aa2025-08-20T03:45:32ZengNature PortfolioScientific Reports2045-23222025-07-0115111410.1038/s41598-025-04184-0Hybrid attention transformer integrated YOLOV8 for fruit ripeness detectionJianyin Tang0Zhenglin Yu1ChangShun Shao2School of Mechanical and Electrical Engineering, Changchun University of Science and TechnologySchool of Mechanical and Electrical Engineering, Changchun University of Science and TechnologySchool of Mechanical and Electrical Engineering, Changchun University of Science and TechnologyAbstract The complexity of the outdoor orchard environment, especially the changes in light intensity and the shadows generated by fruit clusters, present challenges in the identification and classification of mature fruits. To solve these problems, this paper proposes an innovative fruit recognition model, HAT-YOLOV8, aiming to combine the advantages of Hybrid Attention Transformer (HAT) and YOLOV8 deep learning algorithm. This model improves the ability to capture complex dependencies by integrating the Shuffle Attention (SA) module while maintaining low computational complexity. In addition, during the feature fusion stage, the Hybrid Attention Transformer (HAT) module is integrated into TopDownLayer2 to enhance the capture of long-term dependencies and the recovery of detailed information in the input data. To more accurately evaluate the similarity between the prediction box and the real bounding box, this paper uses the EIoU loss function instead of CIoU, thereby improving detection accuracy and accelerating model convergence. In terms of evaluation, this study was experimented on a dataset containing five fruit varieties, each of which was classified into three different maturity levels. The results show that the HAT-YOLOV8 model improved mAP by 11%, 10.2%, 7.6% and 7.8% on the test set, and the overall mAP reached 88.9% respectively. In addition, the HAT-YOLOV8 model demonstrates excellent generalization capabilities, indicating its potential for application in the fields of fruit recognition, maturity assessment and fruit picking automation.https://doi.org/10.1038/s41598-025-04184-0Fruit ripeness detectionHybrid attention transformerYOLOV8sShuffle attentionEIoU
spellingShingle Jianyin Tang
Zhenglin Yu
ChangShun Shao
Hybrid attention transformer integrated YOLOV8 for fruit ripeness detection
Scientific Reports
Fruit ripeness detection
Hybrid attention transformer
YOLOV8s
Shuffle attention
EIoU
title Hybrid attention transformer integrated YOLOV8 for fruit ripeness detection
title_full Hybrid attention transformer integrated YOLOV8 for fruit ripeness detection
title_fullStr Hybrid attention transformer integrated YOLOV8 for fruit ripeness detection
title_full_unstemmed Hybrid attention transformer integrated YOLOV8 for fruit ripeness detection
title_short Hybrid attention transformer integrated YOLOV8 for fruit ripeness detection
title_sort hybrid attention transformer integrated yolov8 for fruit ripeness detection
topic Fruit ripeness detection
Hybrid attention transformer
YOLOV8s
Shuffle attention
EIoU
url https://doi.org/10.1038/s41598-025-04184-0
work_keys_str_mv AT jianyintang hybridattentiontransformerintegratedyolov8forfruitripenessdetection
AT zhenglinyu hybridattentiontransformerintegratedyolov8forfruitripenessdetection
AT changshunshao hybridattentiontransformerintegratedyolov8forfruitripenessdetection