GE-YOLO for Weed Detection in Rice Paddy Fields

Weeds are a significant adverse factor affecting rice growth, and their efficient removal necessitates an accurate, efficient, and well-generalizing weed detection method. However, weed detection faces challenges such as a complex vegetation environment, the similar morphology and color of weeds, an...

Full description

Saved in:
Bibliographic Details
Main Authors: Zimeng Chen, Baifan Chen, Yi Huang, Zeshun Zhou
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2823
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850034838328836096
author Zimeng Chen
Baifan Chen
Yi Huang
Zeshun Zhou
author_facet Zimeng Chen
Baifan Chen
Yi Huang
Zeshun Zhou
author_sort Zimeng Chen
collection DOAJ
description Weeds are a significant adverse factor affecting rice growth, and their efficient removal necessitates an accurate, efficient, and well-generalizing weed detection method. However, weed detection faces challenges such as a complex vegetation environment, the similar morphology and color of weeds, and crops and varying lighting conditions. The current research has yet to address these issues adequately. Therefore, we propose GE-YOLO to identify three common types of weeds in rice fields in the Hunan province of China and to validate its generalization performance. GE-YOLO is an improvement based on the YOLOv8 baseline model. It introduces the Neck network with the Gold-YOLO feature aggregation and distribution network to enhance the network’s ability to fuse multi-scale features and detect weeds of different sizes. Additionally, an EMA attention mechanism is used to better learn weed feature representations, while a GIOU loss function provides smoother gradients and reduces computational complexity. Multiple experiments demonstrate that GE-YOLO achieves 93.1% mAP, 90.3% F1 Score, and 85.9 FPS, surpassing almost all mainstream object detection algorithms such as YOLOv8, YOLOv10, and YOLOv11 in terms of detection accuracy and overall performance. Furthermore, the detection results under different lighting conditions consistently maintained a high level above 90% mAP, and under conditions of heavy occlusion, the average mAP for all weed types reached 88.7%. These results indicate that GE-YOLO has excellent detection accuracy and generalization performance, highlighting the potential of GE-YOLO as a valuable tool for enhancing weed management practices in rice cultivation.
format Article
id doaj-art-940fbb08292c413a8773ad0a4ebc9d3b
institution DOAJ
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-940fbb08292c413a8773ad0a4ebc9d3b2025-08-20T02:57:41ZengMDPI AGApplied Sciences2076-34172025-03-01155282310.3390/app15052823GE-YOLO for Weed Detection in Rice Paddy FieldsZimeng Chen0Baifan Chen1Yi Huang2Zeshun Zhou3School of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaSchool of Automation, Central South University, Changsha 410083, ChinaWeeds are a significant adverse factor affecting rice growth, and their efficient removal necessitates an accurate, efficient, and well-generalizing weed detection method. However, weed detection faces challenges such as a complex vegetation environment, the similar morphology and color of weeds, and crops and varying lighting conditions. The current research has yet to address these issues adequately. Therefore, we propose GE-YOLO to identify three common types of weeds in rice fields in the Hunan province of China and to validate its generalization performance. GE-YOLO is an improvement based on the YOLOv8 baseline model. It introduces the Neck network with the Gold-YOLO feature aggregation and distribution network to enhance the network’s ability to fuse multi-scale features and detect weeds of different sizes. Additionally, an EMA attention mechanism is used to better learn weed feature representations, while a GIOU loss function provides smoother gradients and reduces computational complexity. Multiple experiments demonstrate that GE-YOLO achieves 93.1% mAP, 90.3% F1 Score, and 85.9 FPS, surpassing almost all mainstream object detection algorithms such as YOLOv8, YOLOv10, and YOLOv11 in terms of detection accuracy and overall performance. Furthermore, the detection results under different lighting conditions consistently maintained a high level above 90% mAP, and under conditions of heavy occlusion, the average mAP for all weed types reached 88.7%. These results indicate that GE-YOLO has excellent detection accuracy and generalization performance, highlighting the potential of GE-YOLO as a valuable tool for enhancing weed management practices in rice cultivation.https://www.mdpi.com/2076-3417/15/5/2823weed detectionYOLOv8Gold-YOLOEMAGIOU loss
spellingShingle Zimeng Chen
Baifan Chen
Yi Huang
Zeshun Zhou
GE-YOLO for Weed Detection in Rice Paddy Fields
Applied Sciences
weed detection
YOLOv8
Gold-YOLO
EMA
GIOU loss
title GE-YOLO for Weed Detection in Rice Paddy Fields
title_full GE-YOLO for Weed Detection in Rice Paddy Fields
title_fullStr GE-YOLO for Weed Detection in Rice Paddy Fields
title_full_unstemmed GE-YOLO for Weed Detection in Rice Paddy Fields
title_short GE-YOLO for Weed Detection in Rice Paddy Fields
title_sort ge yolo for weed detection in rice paddy fields
topic weed detection
YOLOv8
Gold-YOLO
EMA
GIOU loss
url https://www.mdpi.com/2076-3417/15/5/2823
work_keys_str_mv AT zimengchen geyoloforweeddetectioninricepaddyfields
AT baifanchen geyoloforweeddetectioninricepaddyfields
AT yihuang geyoloforweeddetectioninricepaddyfields
AT zeshunzhou geyoloforweeddetectioninricepaddyfields