Previous Article in Journal
Dynamic Task Scheduling Optimisation Method for Hilly Orchard Rail Transport Systems
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Agriculture
Volume 15
Issue 24
10.3390/agriculture15242550
agriculture-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Lightweight Segmentation Model for Northern Corn Leaf Blight Based on an Enhanced UNet Architecture

by
Chunyue Ma
1,2,
Chen Wang
1,2,
Xiuru Guo
1,2,
Xiaochen Cui
1,2,
Ruimin Wang
1,2,
Guangdi Xu
1,2,
Yuqi Liu
1,2,
Shouli Zhang
1 and
Zhijun Wang
1,2,*
1
College of Information Science and Engineering, Shandong Agricultural University, Tai’an 271018, China
2
Apple Technology Innovation Center of Shandong Province, Tai’an 271018, China
*
Author to whom correspondence should be addressed.
Agriculture 2025, 15(24), 2550; https://doi.org/10.3390/agriculture15242550 (registering DOI)
Submission received: 22 October 2025 / Revised: 4 December 2025 / Accepted: 7 December 2025 / Published: 9 December 2025
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Versions Notes

Abstract

To address the low segmentation accuracy and high computational complexity of classical deep learning algorithms—caused by the complex morphology of Northern Corn Leaf Blight (NCLB) and blurred boundaries between diseased and healthy leaf regions—this study proposes an improved lightweight segmentation model (termed MSA-UNet) based on the UNet architecture, specifically tailored for NCLB segmentation. In MSA-UNet, three core modules are integrated synergistically to balance efficiency and accuracy: (1) MobileNetV3 (a mobile-optimized convolutional network) replaces the original UNet encoder to reduce parameters while enhancing fine-grained feature extraction; (2) an Enhanced Atrous Spatial Pyramid Pooling (E-ASPP) module is embedded in the bottleneck layer to capture multi-scale lesion features; and (3) the parameter-free Simple Attention Module (SimAM) is added to skip connections to strengthen focus on blurred lesion boundaries. Compared with the baseline UNet model, the proposed MSA-UNet achieves statistically significant performance improvements: mPA, mIoU, and F1-score increase by 3.59%, 5.32%, and 5.75%, respectively; moreover, it delivers substantial reductions in both computational complexity and parameter scale, with GFLOPs decreased by 394.50 G (an 87% reduction) and parameter count reduced by 16.71 M (a 67% reduction). These experimental results confirm that the proposed model markedly improves NCLB leaf lesion segmentation accuracy while retaining a lightweight architecture—rendering it better suited for practical agricultural applications that demand both efficiency and accuracy.
Keywords: northern corn leaf blight image segmentation; improvement of the UNet model; SimAM attention mechanism; multi-scale feature extraction; lightweight northern corn leaf blight image segmentation; improvement of the UNet model; SimAM attention mechanism; multi-scale feature extraction; lightweight

Share and Cite

MDPI and ACS Style

Ma, C.; Wang, C.; Guo, X.; Cui, X.; Wang, R.; Xu, G.; Liu, Y.; Zhang, S.; Wang, Z. A Lightweight Segmentation Model for Northern Corn Leaf Blight Based on an Enhanced UNet Architecture. Agriculture 2025, 15, 2550. https://doi.org/10.3390/agriculture15242550

AMA Style

Ma C, Wang C, Guo X, Cui X, Wang R, Xu G, Liu Y, Zhang S, Wang Z. A Lightweight Segmentation Model for Northern Corn Leaf Blight Based on an Enhanced UNet Architecture. Agriculture. 2025; 15(24):2550. https://doi.org/10.3390/agriculture15242550

Chicago/Turabian Style

Ma, Chunyue, Chen Wang, Xiuru Guo, Xiaochen Cui, Ruimin Wang, Guangdi Xu, Yuqi Liu, Shouli Zhang, and Zhijun Wang. 2025. "A Lightweight Segmentation Model for Northern Corn Leaf Blight Based on an Enhanced UNet Architecture" Agriculture 15, no. 24: 2550. https://doi.org/10.3390/agriculture15242550

APA Style

Ma, C., Wang, C., Guo, X., Cui, X., Wang, R., Xu, G., Liu, Y., Zhang, S., & Wang, Z. (2025). A Lightweight Segmentation Model for Northern Corn Leaf Blight Based on an Enhanced UNet Architecture. Agriculture, 15(24), 2550. https://doi.org/10.3390/agriculture15242550

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop