A Robust YOLOv5 Model with SE Attention and BIFPN for Jishan Jujube Detection in Complex Agricultural Environments

This study presents an improved detection model based on the YOLOv5 (You Only Look Once version 5) framework to enhance the accuracy of Jishan jujube detection in complex natural environments, particularly with varying degrees of occlusion and dense foliage. To improve detection performance, we inte...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Chen, Lijun Su, Yiren Tian, Yixin Chai, Gang Hu, Weiyi Mu
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/6/665
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392752714842112
author Hao Chen
Lijun Su
Yiren Tian
Yixin Chai
Gang Hu
Weiyi Mu
author_facet Hao Chen
Lijun Su
Yiren Tian
Yixin Chai
Gang Hu
Weiyi Mu
author_sort Hao Chen
collection DOAJ
description This study presents an improved detection model based on the YOLOv5 (You Only Look Once version 5) framework to enhance the accuracy of Jishan jujube detection in complex natural environments, particularly with varying degrees of occlusion and dense foliage. To improve detection performance, we integrate an SE (squeeze-and-excitation) attention module into the backbone network to enhance the model’s ability to focus on target objects while suppressing background noise. Additionally, the original neck network is replaced with a BIFPN (bi-directional feature pyramid network) structure, enabling efficient multiscale feature fusion and improving the extraction of critical features, especially for small and occluded fruits. The experimental results demonstrate that the improved YOLOv5 model achieves a mean average precision (mAP) of 96.5%, outperforming the YOLOv3, YOLOv4, YOLOv5, and SSD (Single-Shot Multibox Detector) models by 7.4%, 9.9%, 2.5%, and 0.8%, respectively. Furthermore, the proposed model improves precision (95.8%) and F1 score (92.4%), reducing false positives and achieving a better balance between precision and recall. These results highlight the model’s effectiveness in addressing missed detections of small and occluded fruits while maintaining higher confidence in predictions.
format Article
id doaj-art-14127592e62e49dfa2546166bc33f5fd
institution Kabale University
issn 2077-0472
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-14127592e62e49dfa2546166bc33f5fd2025-08-20T03:40:42ZengMDPI AGAgriculture2077-04722025-03-0115666510.3390/agriculture15060665A Robust YOLOv5 Model with SE Attention and BIFPN for Jishan Jujube Detection in Complex Agricultural EnvironmentsHao Chen0Lijun Su1Yiren Tian2Yixin Chai3Gang Hu4Weiyi Mu5School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Science, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Science, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Science, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Science, Xi’an University of Technology, Xi’an 710048, ChinaThis study presents an improved detection model based on the YOLOv5 (You Only Look Once version 5) framework to enhance the accuracy of Jishan jujube detection in complex natural environments, particularly with varying degrees of occlusion and dense foliage. To improve detection performance, we integrate an SE (squeeze-and-excitation) attention module into the backbone network to enhance the model’s ability to focus on target objects while suppressing background noise. Additionally, the original neck network is replaced with a BIFPN (bi-directional feature pyramid network) structure, enabling efficient multiscale feature fusion and improving the extraction of critical features, especially for small and occluded fruits. The experimental results demonstrate that the improved YOLOv5 model achieves a mean average precision (mAP) of 96.5%, outperforming the YOLOv3, YOLOv4, YOLOv5, and SSD (Single-Shot Multibox Detector) models by 7.4%, 9.9%, 2.5%, and 0.8%, respectively. Furthermore, the proposed model improves precision (95.8%) and F1 score (92.4%), reducing false positives and achieving a better balance between precision and recall. These results highlight the model’s effectiveness in addressing missed detections of small and occluded fruits while maintaining higher confidence in predictions.https://www.mdpi.com/2077-0472/15/6/665YOLOv5SE attention mechanismBIFPNJishan jujube detectionprecision agriculture
spellingShingle Hao Chen
Lijun Su
Yiren Tian
Yixin Chai
Gang Hu
Weiyi Mu
A Robust YOLOv5 Model with SE Attention and BIFPN for Jishan Jujube Detection in Complex Agricultural Environments
Agriculture
YOLOv5
SE attention mechanism
BIFPN
Jishan jujube detection
precision agriculture
title A Robust YOLOv5 Model with SE Attention and BIFPN for Jishan Jujube Detection in Complex Agricultural Environments
title_full A Robust YOLOv5 Model with SE Attention and BIFPN for Jishan Jujube Detection in Complex Agricultural Environments
title_fullStr A Robust YOLOv5 Model with SE Attention and BIFPN for Jishan Jujube Detection in Complex Agricultural Environments
title_full_unstemmed A Robust YOLOv5 Model with SE Attention and BIFPN for Jishan Jujube Detection in Complex Agricultural Environments
title_short A Robust YOLOv5 Model with SE Attention and BIFPN for Jishan Jujube Detection in Complex Agricultural Environments
title_sort robust yolov5 model with se attention and bifpn for jishan jujube detection in complex agricultural environments
topic YOLOv5
SE attention mechanism
BIFPN
Jishan jujube detection
precision agriculture
url https://www.mdpi.com/2077-0472/15/6/665
work_keys_str_mv AT haochen arobustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT lijunsu arobustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT yirentian arobustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT yixinchai arobustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT ganghu arobustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT weiyimu arobustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT haochen robustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT lijunsu robustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT yirentian robustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT yixinchai robustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT ganghu robustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments
AT weiyimu robustyolov5modelwithseattentionandbifpnforjishanjujubedetectionincomplexagriculturalenvironments