GhostConv+CA-YOLOv8n: a lightweight network for rice pest detection based on the aggregation of low-level features in real-world complex backgrounds

Deep learning models for rice pest detection often face performance degradation in real-world field environments due to complex backgrounds and limited computational resources. Existing approaches suffer from two critical limitations: (1) inadequate feature representation under occlusion and scale v...

Full description

Saved in:
Bibliographic Details
Main Authors: Fei Li, Yang Lu, Qiang Ma, Shuxin Yin, Rui Zhao
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1620339/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239885959921664
author Fei Li
Yang Lu
Qiang Ma
Shuxin Yin
Rui Zhao
author_facet Fei Li
Yang Lu
Qiang Ma
Shuxin Yin
Rui Zhao
author_sort Fei Li
collection DOAJ
description Deep learning models for rice pest detection often face performance degradation in real-world field environments due to complex backgrounds and limited computational resources. Existing approaches suffer from two critical limitations: (1) inadequate feature representation under occlusion and scale variations, and (2) excessive computational costs for edge deployment. To overcome these limitations, this paper introduces GhostConv+CA-YOLOv8n, a lightweight object detection framework was proposed, which incorporates several innovative features: GhostConv replaces standard convolutional operations with computationally efficient ghost modules in the YOLOv8n’s backbone structure, reducing parameters by 40,458 while maintaining feature richness; a Context Aggregation (CA) module is applied after the large and medium-sized feature maps were output by the YOLOv8n’s neck structure. This module enhance low-level feature representation by fusing global and local context, which is particularly effective for detecting occluded pests in complex environments; Shape-IoU, which improves bounding box regression by accounting for target morphology, and Slide Loss, which addresses class imbalance by dynamically adjusting sample weighting during training were employed. Comprehensive evaluations on the Ricepest15 dataset, GhostConv+CA-YOLOv8n achieves 89.959% precision and 82.258% recall with improvements of 3.657% and 11.59%, and the model parameter reduced 1.34%, over the YOLOv8n baseline while maintaining a high mAP (94.527% vs. 84.994% baseline). Furthermore, the model shows strong generalization, achieving a 4.49%, 5.452%, and 3.407% improvement in F1-score, precision, and recall on the IP102 benchmark. This study bridges the gap between accuracy and efficiency for in field pest detection, providing a practical solution for real-time rice monitoring in smart agriculture systems.
format Article
id doaj-art-73fe596fc74448c69a9bc463afc7d69b
institution Kabale University
issn 1664-462X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-73fe596fc74448c69a9bc463afc7d69b2025-08-20T04:00:49ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-08-011610.3389/fpls.2025.16203391620339GhostConv+CA-YOLOv8n: a lightweight network for rice pest detection based on the aggregation of low-level features in real-world complex backgroundsFei LiYang LuQiang MaShuxin YinRui ZhaoDeep learning models for rice pest detection often face performance degradation in real-world field environments due to complex backgrounds and limited computational resources. Existing approaches suffer from two critical limitations: (1) inadequate feature representation under occlusion and scale variations, and (2) excessive computational costs for edge deployment. To overcome these limitations, this paper introduces GhostConv+CA-YOLOv8n, a lightweight object detection framework was proposed, which incorporates several innovative features: GhostConv replaces standard convolutional operations with computationally efficient ghost modules in the YOLOv8n’s backbone structure, reducing parameters by 40,458 while maintaining feature richness; a Context Aggregation (CA) module is applied after the large and medium-sized feature maps were output by the YOLOv8n’s neck structure. This module enhance low-level feature representation by fusing global and local context, which is particularly effective for detecting occluded pests in complex environments; Shape-IoU, which improves bounding box regression by accounting for target morphology, and Slide Loss, which addresses class imbalance by dynamically adjusting sample weighting during training were employed. Comprehensive evaluations on the Ricepest15 dataset, GhostConv+CA-YOLOv8n achieves 89.959% precision and 82.258% recall with improvements of 3.657% and 11.59%, and the model parameter reduced 1.34%, over the YOLOv8n baseline while maintaining a high mAP (94.527% vs. 84.994% baseline). Furthermore, the model shows strong generalization, achieving a 4.49%, 5.452%, and 3.407% improvement in F1-score, precision, and recall on the IP102 benchmark. This study bridges the gap between accuracy and efficiency for in field pest detection, providing a practical solution for real-time rice monitoring in smart agriculture systems.https://www.frontiersin.org/articles/10.3389/fpls.2025.1620339/fullrice pest detectionGhostConvcontext aggregation blockShape-IoUSlide Loss
spellingShingle Fei Li
Yang Lu
Qiang Ma
Shuxin Yin
Rui Zhao
GhostConv+CA-YOLOv8n: a lightweight network for rice pest detection based on the aggregation of low-level features in real-world complex backgrounds
Frontiers in Plant Science
rice pest detection
GhostConv
context aggregation block
Shape-IoU
Slide Loss
title GhostConv+CA-YOLOv8n: a lightweight network for rice pest detection based on the aggregation of low-level features in real-world complex backgrounds
title_full GhostConv+CA-YOLOv8n: a lightweight network for rice pest detection based on the aggregation of low-level features in real-world complex backgrounds
title_fullStr GhostConv+CA-YOLOv8n: a lightweight network for rice pest detection based on the aggregation of low-level features in real-world complex backgrounds
title_full_unstemmed GhostConv+CA-YOLOv8n: a lightweight network for rice pest detection based on the aggregation of low-level features in real-world complex backgrounds
title_short GhostConv+CA-YOLOv8n: a lightweight network for rice pest detection based on the aggregation of low-level features in real-world complex backgrounds
title_sort ghostconv ca yolov8n a lightweight network for rice pest detection based on the aggregation of low level features in real world complex backgrounds
topic rice pest detection
GhostConv
context aggregation block
Shape-IoU
Slide Loss
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1620339/full
work_keys_str_mv AT feili ghostconvcayolov8nalightweightnetworkforricepestdetectionbasedontheaggregationoflowlevelfeaturesinrealworldcomplexbackgrounds
AT yanglu ghostconvcayolov8nalightweightnetworkforricepestdetectionbasedontheaggregationoflowlevelfeaturesinrealworldcomplexbackgrounds
AT qiangma ghostconvcayolov8nalightweightnetworkforricepestdetectionbasedontheaggregationoflowlevelfeaturesinrealworldcomplexbackgrounds
AT shuxinyin ghostconvcayolov8nalightweightnetworkforricepestdetectionbasedontheaggregationoflowlevelfeaturesinrealworldcomplexbackgrounds
AT ruizhao ghostconvcayolov8nalightweightnetworkforricepestdetectionbasedontheaggregationoflowlevelfeaturesinrealworldcomplexbackgrounds