BCS_YOLO: Research on Corn Leaf Disease and Pest Detection Based on YOLOv11n

Frequent corn leaf diseases and pests pose serious threats to agricultural production. Traditional manual detection methods suffer from significant limitations in both performance and efficiency. To address this, the present paper proposes a novel biotic condition screening (BCS) model for the detec...

Full description

Saved in:
Bibliographic Details
Main Authors: Shengnan Hao, Erjian Gao, Zhanlin Ji, Ivan Ganchev
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/15/8231
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Frequent corn leaf diseases and pests pose serious threats to agricultural production. Traditional manual detection methods suffer from significant limitations in both performance and efficiency. To address this, the present paper proposes a novel biotic condition screening (BCS) model for the detection of corn leaf diseases and pests, called BCS_YOLO, based on the You Only Look Once version 11n (YOLOv11n). The proposed model enables accurate detection and classification of various corn leaf pathologies and pest infestations under challenging agricultural field conditions. It achieves this thanks to three key newly designed modules—a Self-Perception Coordinated Global Attention (SPCGA) module, a High/Low-Frequency Feature Enhancement (HLFFE) module, and a Local Attention Enhancement (LAE) module. The SPCGA module improves the model’s ability to perceive fine-grained targets by fusing multiple attention mechanisms. The HLFFE module adopts a frequency domain separation strategy to strengthen edge delineation and structural detail representation in affected areas. The LAE module effectively improves the model’s discrimination ability between targets and backgrounds through local importance calculation and intensity adjustment mechanisms. Conducted experiments show that BCS_YOLO achieves 78.4%, 73.7%, 76.0%, and 82.0% in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>c</mi><mi>i</mi><mi>s</mi><mi>i</mi><mi>o</mi><mi>n</mi></mrow></semantics></math></inline-formula>, <i>recall</i>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>F</mi><mn>1</mn><mtext> </mtext><mi>s</mi><mi>c</mi><mi>o</mi><mi>r</mi><mi>e</mi></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>m</mi><mi>A</mi><mi>P</mi><mo>@</mo><mn>50</mn></mrow></semantics></math></inline-formula>, respectively, representing corresponding improvements of 3.0%, 3.3%, 3.2%, and 4.6% compared to the baseline model (YOLOv11n), while also outperforming the mainstream object detection models. In summary, the proposed BCS_YOLO model provides a practical and scalable solution for efficient detection of corn leaf diseases and pests in complex smart-agriculture scenarios, demonstrating significant theoretical and application value.
ISSN:2076-3417