Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention Mechanism

Northern corn leaf blight (NCLB) is caused by a fungus and can be susceptible to the disease throughout the growing period of corn, posing a significant impact on corn yield. Aiming at the problems of under-segmentation, over-segmentation, and low segmentation accuracy in the traditional segmentatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Ye Mu, Ke Li, Yu Sun, Yu Bao
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/14/11/2652
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850149629663903744
author Ye Mu
Ke Li
Yu Sun
Yu Bao
author_facet Ye Mu
Ke Li
Yu Sun
Yu Bao
author_sort Ye Mu
collection DOAJ
description Northern corn leaf blight (NCLB) is caused by a fungus and can be susceptible to the disease throughout the growing period of corn, posing a significant impact on corn yield. Aiming at the problems of under-segmentation, over-segmentation, and low segmentation accuracy in the traditional segmentation model of northern corn leaf blight, this study proposes a segmentation method based on an improved U-Net network model. By introducing a convolutional layer and maximum pooling layer to a VGG19 network, the channel attention module and spatial attention module (CBAM) are fused, and the squeeze excitation (SE) attention mechanism is combined. This enhances image feature decoding, integrates feature maps of each layer, strengthens the feature extraction process, expands the sensory fields and aggregates context information, and reduces the loss of location and dense semantic information caused by the pooling operation. Findings from the study show that the proposed NCLB-Net has significantly improved the MIoU and PA indexes, reaching 92.43% and 94.71%, respectively. Compared with the traditional methods, U-Net, SETR, DAnet, OCnet, PSPNet, etc., the MIoU is improved by 20.81%, 16.10%, 9.79%, 5.27%, and 11.06%, and the PA is improved by 11.49%, 8.18%, 9.54%, 13.11%, and 6.26%, respectively.
format Article
id doaj-art-82d6f38b80b7450da3a7001debfad0ee
institution OA Journals
issn 2073-4395
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-82d6f38b80b7450da3a7001debfad0ee2025-08-20T02:26:51ZengMDPI AGAgronomy2073-43952024-11-011411265210.3390/agronomy14112652Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention MechanismYe Mu0Ke Li1Yu Sun2Yu Bao3College of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Life Science, Changchun Normal University, Changchun 130118, ChinaNorthern corn leaf blight (NCLB) is caused by a fungus and can be susceptible to the disease throughout the growing period of corn, posing a significant impact on corn yield. Aiming at the problems of under-segmentation, over-segmentation, and low segmentation accuracy in the traditional segmentation model of northern corn leaf blight, this study proposes a segmentation method based on an improved U-Net network model. By introducing a convolutional layer and maximum pooling layer to a VGG19 network, the channel attention module and spatial attention module (CBAM) are fused, and the squeeze excitation (SE) attention mechanism is combined. This enhances image feature decoding, integrates feature maps of each layer, strengthens the feature extraction process, expands the sensory fields and aggregates context information, and reduces the loss of location and dense semantic information caused by the pooling operation. Findings from the study show that the proposed NCLB-Net has significantly improved the MIoU and PA indexes, reaching 92.43% and 94.71%, respectively. Compared with the traditional methods, U-Net, SETR, DAnet, OCnet, PSPNet, etc., the MIoU is improved by 20.81%, 16.10%, 9.79%, 5.27%, and 11.06%, and the PA is improved by 11.49%, 8.18%, 9.54%, 13.11%, and 6.26%, respectively.https://www.mdpi.com/2073-4395/14/11/2652northern corn leaf blightsegmentationattention mechanismU-Net networkimage segmentationmaize disease
spellingShingle Ye Mu
Ke Li
Yu Sun
Yu Bao
Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention Mechanism
Agronomy
northern corn leaf blight
segmentation
attention mechanism
U-Net network
image segmentation
maize disease
title Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention Mechanism
title_full Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention Mechanism
title_fullStr Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention Mechanism
title_full_unstemmed Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention Mechanism
title_short Semantic Segmentation of Corn Leaf Blotch Disease Images Based on U-Net Integrated with RFB Structure and Dual Attention Mechanism
title_sort semantic segmentation of corn leaf blotch disease images based on u net integrated with rfb structure and dual attention mechanism
topic northern corn leaf blight
segmentation
attention mechanism
U-Net network
image segmentation
maize disease
url https://www.mdpi.com/2073-4395/14/11/2652
work_keys_str_mv AT yemu semanticsegmentationofcornleafblotchdiseaseimagesbasedonunetintegratedwithrfbstructureanddualattentionmechanism
AT keli semanticsegmentationofcornleafblotchdiseaseimagesbasedonunetintegratedwithrfbstructureanddualattentionmechanism
AT yusun semanticsegmentationofcornleafblotchdiseaseimagesbasedonunetintegratedwithrfbstructureanddualattentionmechanism
AT yubao semanticsegmentationofcornleafblotchdiseaseimagesbasedonunetintegratedwithrfbstructureanddualattentionmechanism