LeafDPN: An Improved DPN Model for the Identification of Bacterial Blight in Soybean in Natural Environments DOI Creative Commons
Rui Cong,

Ying Xu,

Hao Su

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(12), P. 3064 - 3064

Published: Dec. 22, 2024

Bacterial blight of soybean (BBS), caused by Pseudomonas syringae pv. glycinea, is one the most devastating diseases in with significant yield losses ranging from 4% to 40%. The timely detection BBS foundation for disease control. However, traditional identification methods are inefficient and rely heavily on expert knowledge. Existing automated approaches have not achieved high accuracy natural environments often require advanced equipment extensive training, limiting their practicality adaptability. To overcome these challenges, we propose LeafDPN, an improved Dual-Path Network model enhanced Vision Transformer blocks forward propagation function SE ConvBNLayer. These enhancements model’s accuracy, receptive field, feature expression capabilities. Experiments conducted a self-constructed dataset 864 expert-labeled images across three types demonstrated that LeafDPN 98.96% shorted iteration time just 24 epochs. It outperformed 14 baseline models like HRNet EfficientNet terms training efficiency, resource consumption. In addition, proposed has potential be applied other plant based available datasets.

Language: Английский

AppleYOLO: Apple yield estimation method using improved YOLOv8 based on Deep OC-SORT DOI

Shiting Tan,

Zhufang Kuang,

Boyu Jin

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 126764 - 126764

Published: Feb. 1, 2025

Language: Английский

Citations

1
Wheat Fusarium Head Blight Automatic Non-Destructive Detection Based on Multi-Scale Imaging: A Technical Perspective DOI Creative Commons

Guoqing Feng,

Ying Gu, Cheng Wang

et al.

Plants, Journal Year: 2024, Volume and Issue: 13(13), P. 1722 - 1722

Published: June 21, 2024

Fusarium head blight (FHB) is a major threat to global wheat production. Recent reviews of FHB focused on pathology or comprehensive prevention and lacked summary advanced detection techniques. Unlike traditional management methods, based various imaging technologies has the obvious advantages high degree automation efficiency. With rapid development computer vision deep learning technology, number related research grown explosively in recent years. This review begins with an overview epidemic mechanisms changes characteristics infected wheat. On this basis, scales are divided into microscopic, medium, submacroscopic, macroscopic scales. Then, we outline relevant articles, algorithms, methodologies about from disease qualitative analysis summarize potential difficulties practicalization corresponding technology. paper could provide researchers more targeted technical support breakthrough directions. Additionally, provides ideal application mode multi-scale then examines trend all-scale system, which paved way for fusion non-destructive imaging.

Language: Английский

Citations

5
An innovative fusion method with micro-vision and spectrum of wheat for detecting asymptomatic Fusarium head blight DOI
Jianghui Xiong,

Shangfeng Gu,

Yuan Rao

et al.

Journal of Food Composition and Analysis, Journal Year: 2025, Volume and Issue: unknown, P. 107258 - 107258

Published: Jan. 1, 2025

Language: Английский

Citations

0
A generalizable and interpretable model for early warning of pest-induced crop diseases using environmental data DOI

D. R. Wadhwa,

Kamal Malik

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 227, P. 109472 - 109472

Published: Oct. 3, 2024

Language: Английский

Citations

3
Comprehensive wheat lodging detection under different UAV heights using machine/deep learning models DOI

Jianing Long,

Zhao Zhang, Qu Zhang

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 231, P. 109972 - 109972

Published: Jan. 28, 2025

Language: Английский

Citations

0
Advanced deep learning model for crop-specific and cross-crop pest identification DOI
Md Suzauddola, Defu Zhang, Adnan Zeb

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: 274, P. 126896 - 126896

Published: Feb. 24, 2025

Language: Английский

Citations

0
Effective Strategies for Managing Wheat Diseases: Mapping Academic Literature Utilizing VOSviewer and Insights from Our 15 Years of Research DOI Creative Commons
Ioannis Vagelas

Agrochemicals, Journal Year: 2025, Volume and Issue: 4(1), P. 4 - 4

Published: March 4, 2025

Wheat pathogens pose a significant risk to global wheat production, with climate change further complicating disease dynamics. Effective management requires combination of genetic resistance, cultural practices, and careful use chemical controls. Ongoing research adaptation changing environmental conditions are crucial for sustaining yields food security. Based on selective academic literature retrieved from the Scopus database analyzed by bibliographic software such as VOSviewer we discussed focused various aspects current future strategies managing major diseases Tan spot, Septoria tritici blotch, Fusarium head blight, etc. Chemical methods, fungicides, can be effective but not always preferred. Instead, agronomic practices like crop rotation tillage play role in reducing both incidence severity these diseases. Moreover, adopting resistance is essential management.

Language: Английский

Citations

0
Wheat FHB resistance assessment using hyperspectral feature band image fusion and deep learning DOI Creative Commons
Kun Liang,

Ren Zhizhou,

Song Jinpeng

et al.

International journal of agricultural and biological engineering, Journal Year: 2024, Volume and Issue: 17(2), P. 240 - 249

Published: Jan. 1, 2024

The breeding and selection of resistant varieties is an effective way to minimize wheat Fusarium head blight (FHB) hazards, so it important identify evaluate varieties. traditional resistance phenotype identification still largely dependent on time-consuming manual methods. In this paper, the method for evaluating FHB in ears was optimized based fusion feature wavelength images hyperspectral imaging system Faster R-CNN algorithm. spectral data from 400-1000 nm were preprocessed by multiple scattering correction (MSC) Three wavelengths (553 nm, 682 714 nm) selected analyzing X-loading weights (XLW) according absolute value peaks troughs different principal component (PC) load coefficient curves. Then, methods three explored with weight coefficients. trained RGB datasets VGG16, AlexNet, ZFNet, ResNet-50 networks separately. other detection models SSD, YOLOv5, YOLOv7, CenterNet, RetinaNet used compare model. As a result, VGG16 best mAP (mean Average Precision) ranged 97.7% 98.8%. model showed performance Fusion Image-1 dataset. Moreover, achieved average accuracy 99.00%, which 23.89%, 1.21%, 0.75%, 0.62%, 8.46% higher than models. Therefore, demonstrated that image dataset proposed paper feasible rapid evaluation resistance. This study provided ensuring food security. Key words: Fusariumhead blight, evaluation, band fusion, deep learning, DOI: 10.25165/j.ijabe.20241702.8269 Citation: Liang K, Ren Z Z, Song J P, Yuan R, Zhang Q. Wheat assessment using bandimage learning. Int Agric & Biol Eng, 2024; 17(2): 240–249.

Language: Английский

Citations

2
Lca-Med: A Lightweight Cross-Modal Adaptive Feature Processing Module for Detecting Imbalanced Medical Image Distribution DOI
Xiang Li, Long Lan, Husam Lahza

et al.

Published: Jan. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Language: Английский

Citations

0
YOLOv5s-ECCW: A Lightweight Detection Model for Sugarcane Smut in Natural Environments DOI Creative Commons
Min Yu,

Fengbing Li,

Xiu‐Peng Song

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(10), P. 2327 - 2327

Published: Oct. 10, 2024

Sugarcane smut, a serious disease caused by the fungus Sporosorium scitamineum, can result in 30% to 100% cane loss. The most affordable and efficient measure of preventing handling sugarcane smut is select disease-resistant varieties. A comprehensive evaluation resistance based on incidence essential during selection process, necessitating rapid accurate identification smut. Traditional methods, which rely visual observation symptoms, are time-consuming, costly, inefficient. To address these limitations, we present lightweight detection model (YOLOv5s-ECCW), incorporates several innovative features. Specifically, EfficientNetV2 incorporated into YOLOv5 network achieve compression while maintaining high accuracy. convolutional block attention mechanism (CBAM) added backbone improve its feature extraction capability suppress irrelevant information. C3STR module used replace C3 module, enhancing ability capture global large targets. WIoU loss function place CIoU one bounding box regression’s experimental results demonstrate that YOLOv5s-ECCW achieves mean average precision (mAP) 97.8% with only 4.9 G FLOPs 3.25 M parameters. Compared original YOLOv5, our improvements include 0.2% increase mAP, 54% reduction parameters, 70.3% decrease computational requirements. proposed outperforms YOLOv4, SSD, YOLOv8 terms accuracy, efficiency, size. meets urgent need for real-time supporting better management resistant

Language: Английский

Citations

0