An Integrated Multi-Model Fusion System for Automatically Diagnosing the Severity of Wheat Fusarium Head Blight

Article Agronomy

GSEYOLOX-s: An Improved Lightweight Network for Identifying the Severity of Wheat Fusarium Head Blight

Rui Mao et al.

Summary: A lightweight GSEYOLOX-s model was proposed to automatically recognize the severity of FHB, achieving high performance and real-time identification on mobile terminals, which facilitates the precise management of crop diseases.

AGRONOMY-BASEL (2023)

Add to Collection

Article Environmental Sciences

Quantitative Evaluation of Maize Emergence Using UAV Imagery and Deep Learning

Minguo Liu et al.

Remote Sensing (2023)

Add to Collection

Article Agriculture, Multidisciplinary

Enhancing wheat Fusarium head blight detection using rotation Yolo wheat detection network and simple spatial attention network

Dong-Yan Zhang et al.

Summary: This study introduced two new networks, the Rotation Yolo Wheat Detection (RYWD) network and the Simple Spatial Attention (SSA) network, to improve the detection accuracy of Fusarium head blight (FHB) in wheat. The RYWD network served as a novel rotation detector capable of detecting wheat head images with detection boxes of arbitrary orientations, while the SSA network incorporated a spatial attention module and a spatial continuity loss to extract wheat features based on their spatial distribution. The proposed method achieved a high accuracy of 94.66% in predicting FHB levels across two different years and locations, outperforming previous research.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2023)

Add to Collection

Article Ecology

The orange wheat blossom midge promotes fusarium head blight disease, posing a risk to wheat production in northern China

Jin Miao et al.

Summary: This study investigated the interactions between the orange wheat blossom midge (OWBM) and Fusarium head blight (FHB) on wheat ears. It found that simultaneous infection of OWBM and FHB greatly increased disease severity and OWBM performance, while reducing yield.

ACTA ECOLOGICA SINICA (2023)

Add to Collection

Review Computer Science, Information Systems

Deep learning in wheat diseases classification: A systematic review

Deepak Kumar et al.

Summary: The paper systematically reviews recent studies on WD prediction models, focusing mainly on wheat stripe rust. The results indicate that accuracy is the most prominent performance metric, and artificial neural networks are the most commonly used prediction technique.

MULTIMEDIA TOOLS AND APPLICATIONS (2022)

Add to Collection

Article Environmental Sciences

Two-Stage Convolutional Neural Networks for Diagnosing the Severity of Alternaria Leaf Blotch Disease of the Apple Tree

Bo-Yuan Liu et al.

Summary: In this study, deep learning algorithms were used to assess the severity of apple Alternaria leaf blotch. The PSPNet model with MobileNetV2 backbone achieved the highest performance in leaf segmentation, while the UNet model with VGG backbone performed the best in disease-area prediction. The results showed high accuracy and consistency, providing technical support for precise application of pesticides.

REMOTE SENSING (2022)

Add to Collection

Article Agriculture, Multidisciplinary

A deep learning method for oriented and small wheat spike detection (OSWSDet) in UAV images

Jianqing Zhao et al.

Summary: This paper proposes a deep learning method (OSWSDet) for detecting wheat spikes in UAV images, which introduces the orientation and a micro-scale detection layer to improve detection accuracy. Experimental results show that OSWSDet achieves high accuracy in complex backgrounds.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

Add to Collection

Article Environmental Sciences

A Lightweight Model for Wheat Ear Fusarium Head Blight Detection Based on RGB Images

Qingqing Hong et al.

Summary: This paper proposes a lightweight model for wheat ear FHB detection based on UAV-enabled edge computing. The model utilizes deep learning architectures and edge devices to achieve accurate and real-time detection. By using a lighter network, optimizing the loss function, and enhancing the model's generalization ability, the proposed model performs well in terms of detection accuracy.

REMOTE SENSING (2022)

Add to Collection

Article Agronomy

Estimation of Fusarium Head Blight Severity Based on Transfer Learning

Chunfeng Gao et al.

Summary: This study proposes a method based on transfer learning and convolutional neural networks (CNNs) for accurately estimating the severity of wheat Fusarium head blight (FHB). The results show that the ResNet50 model performs the best in terms of accuracy and F1 score under transfer learning and data augmentation.

AGRONOMY-BASEL (2022)

Add to Collection

Article Agriculture, Multidisciplinary

Applying convolutional neural networks for detecting wheat stripe rust transmission centers under complex field conditions using RGB-based high spatial resolution images from UAVs

Jie Deng et al.

Summary: This study explores the use of UAV and RGB-based high spatial resolution images, along with convolutional neural networks, to detect the occurrence of wheat stripe rust transmission centers in complex field conditions. The results demonstrate the capability of UAV imaging in accurately detecting wheat stripe rust. Additionally, the study evaluates the impact of classification framework and spatial resolution on model accuracy.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

Add to Collection

Article Agriculture, Multidisciplinary

A segmentation network for smart weed management in wheat fields

Kunlin Zou et al.

Summary: This paper presents a modified U-net approach for segmenting weeds and wheat in images. Experimental results show that the method can effectively and accurately perform the segmentation task, which has significant implications for precision weeding.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

Add to Collection

Review Agronomy

Convolutional Neural Networks in Computer Vision for Grain Crop Phenotyping: A Review

Ya-Hong Wang et al.

Summary: Computer vision combined with deep convolutional neural networks is a reliable method for characterizing and quantifying high-throughput phenotyping of different grain crops. Developing corresponding imaging systems can increase stakeholders' confidence in grain crop cultivation, bringing technical and economic benefits.

AGRONOMY-BASEL (2022)

Add to Collection

Article Agronomy

Automatic Tandem Dual BlendMask Networks for Severity Assessment of Wheat Fusarium Head Blight

Yichao Gao et al.

Summary: This study utilized an automatic deep learning model to achieve fast detection and segmentation of wheat spikes and diseased areas, enabling the assessment of disease severity in wheat resistant varieties. The results demonstrate high precision and recall rates of the model, highlighting the significance of visual and intelligent disease resistance screening.

AGRICULTURE-BASEL (2022)

Add to Collection

Proceedings Paper Computer Science, Interdisciplinary Applications

Safety Helmet Detection Using Deep Learning: Implementation and Comparative Study Using YOLOv5, YOLOv6, and YOLOv7

Nigel Dale Then Yung et al.

Summary: This review paper evaluates and studies the performance of different deep learning algorithms in safety helmet detection tasks. The results show that the YOLOv5s (small) model, YOLOv6s (small) model, and YOLOv7 model perform well.

2022 INTERNATIONAL CONFERENCE ON GREEN ENERGY, COMPUTING AND SUSTAINABLE TECHNOLOGY (GECOST) (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Optimized HRNet for image semantic segmentation

Huisi Wu et al.

Summary: This paper introduces an optimized high-resolution net (HRNet) for image semantic segmentation. By incorporating mixed dilated convolution (MDC) module and multi-level data-dependent feature aggregation (MDFA) module, the network shows improved capability in recognizing objects with various scales and irregular shapes.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Add to Collection

Article Agriculture, Multidisciplinary

Lightweight convolutional neural network model for field wheat ear disease identification

Wenxia Bao et al.

Summary: Manual diagnosis of crop diseases is costly and inefficient, prompting the development of a lightweight CNN model called SimpleNet for automatic identification of wheat ear diseases. SimpleNet incorporates features like Convolutional Block Attention Module and feature fusion module, achieving high identification accuracy of 94.1% on test data set, surpassing classic and lightweight CNN models.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

Add to Collection

Article Environmental Sciences

Automatic Evaluation of Wheat Resistance to Fusarium Head Blight Using Dual Mask-RCNN Deep Learning Frameworks in Computer Vision

Wen-Hao Su et al.

Summary: This study demonstrates the feasibility of rapidly determining levels of FHB in wheat spikes using Mask region convolutional neural network (Mask-RCNN), which allows for reliable identification of the symptom location and the disease severity of wheat spikes. This method enables the rapid and efficient automatic recognition of wheat spikes and FHB diseased areas.

REMOTE SENSING (2021)

Add to Collection

Article Chemistry, Analytical

A Deep-Learning-Based Approach for Wheat Yellow Rust Disease Recognition from Unmanned Aerial Vehicle Images

Qian Pan et al.

Summary: This study proposed a deep learning-based method for efficiently identifying wheat yellow rust from UAV images, achieving a recognition accuracy of 98%. Additionally, the use of high-accuracy classification results from traditional algorithms as weak samples improved the labeling problem for large-size images, with a final recognition accuracy of 94%.

SENSORS (2021)

Add to Collection

Article Chemistry, Applied

Hyperspectral imaging and improved feature variable selection for automated determination of deoxynivalenol in various genetic lines of barley kernels for resistance screening

Wen-Hao Su et al.

Summary: Fusarium head blight (FHB) caused by Fusarium graminearum leads to reduced yields and decreased grain value due to the presence of deoxynivalenol (DON). This study explored the feasibility of using hyperspectral imaging for rapid and non-destructive assay of DON in barley kernels, demonstrating potential for accelerating non-destructive DON assays of barley samples.

FOOD CHEMISTRY (2021)

Add to Collection

Review Food Science & Technology