检索结果-内蒙古大学图书馆

pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy

PLANT METHODS 2025年第1期21卷 1-23页

作者： Fu, Rui Wang, Shiyu Dong, Mingqiu Sun, Hao Al-Absi, Mohammed Abdulhakim Zhang, Kaijie Chen, Qian Xiao, Liqun Wang, Xuewei Li, Ye Weifang Univ Sci & Technol Shandong Facil Hort Bioengn Res Ctr Weifang 262700 Peoples R China Sichuan Int Studies Univ Chongqing 400031 Peoples R China Beijing Inst Technol Beijing 100081 Peoples R China Kyungdong Univ Dept Smart Comp 46 4 Gil Giosung 24764 Gangwondo South Korea Sichuan Technol & Business Univ Chengdu 610000 Sichuan Peoples R China Southwest Jiaotong Univ Chengdu 610000 Sichuan Peoples R China

pest management is essential for agricultural production and food security, as pests can cause significant crop losses and economic impact. Early pest detection is key to timely intervention. While object detection models perform well on various datasets, they assume i.i.d. data, which is often not the case in diverse real-world environments, leading to decreased accuracy. To solve the problem, we propose the CrossDomain-pestDetect (CDPD) method, which is based on the YOLOv9 model and incorporates a test-time adaptation (TTA) framework. CDPD includes Dynamic Data Augmentation (DynamicDA), a Dynamic Adaptive Gate (DAG), and a Multi-Task Dynamic Adaptation Model (MT-DAM). Our DynamicDA enhances images for each batch by combining strong and weak augmentations. The MT-DAM integrates an object detection model with an image segmentation model, exchanging information through feature fusion at the feature extraction layer. During testing, test-time adaptation updates both models, continuing feature fusion during forward propagation. DAG adaptively controls the degree of feature fusion to improve detection capabilities. Self-supervised learning enables the model to adapt during testing to changing environments. Experiments show that without test-time adaptation, our method achieved a 7.6% increase in mAP50 over the baseline in the original environment and a 16.1% increase in the target environment. Finally, with test-time adaptation, the mAP50 score in the unseen target environment reaches 73.8%, which is a significant improvement over the baseline.

关键词： pest detection Unseen environment Domain adaptation Test-time adaptation Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A transformer-based model with feature compensation and local information enhancement for end-to-end pest detection

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2025年 231卷

作者： Liu, Honglin Zhan, Yongzhao Sun, Jun Mao, Qirong Wu, Tongwang Jiangsu Univ Sch Comp Sci & Commun Engn Zhenjiang 212013 Jiangsu Peoples R China Jiangsu Engn Res Ctr Big Data Ubiquitous Percept & Zhenjiang Peoples R China Jiangsu Univ Sch Elect & Informat Engn Zhenjiang 212013 Jiangsu Peoples R China

The development of accurate and robust pest detection is a crucial step toward reliable forecasting of agricultural pests in precision agriculture and has gained significant attention in many countries. Compared to conventional object detection, pest detection faces greater challenges in recognizing fine details. This is because pests often have small and intricate identifying features, such as antennae, legs, or specific body markings, which maybe easily lost during the feature extraction process. Furthermore, pest detection must deal with more complex environmental information, which includes plant species, different parts of plants, and growth stages of plants. Therefore, we propose an end-to-end pest detection method using feature representation compensation (FRC) and regional pale-shaped self-attention (RPSA). In this method, we designed an FRC module based on CSWin, which can compensate for the loss of feature information caused by the down- sampling process. This module can significantly improve the performance of pest detection models without increasing the computational load. To further improve the performance, a transformer encoder based on RPSA is proposed to capture global information and enhance local information of the feature map, which can organically combine the global and local features of the image and achieve more comprehensive feature representations. Finally, extensive experiments are conducted on IP102 and FPD to validate the effectiveness of our method. The mAP scores achieved by our method surpass that of the state-of-the-art CNN-based methods by 4.5% and 5.7% on the IP102 and FPD, respectively. The source code and pre-trained models are available at https://***/LionelLinH/FRC-and-RPSA-for-pest-detection.

关键词： pest detection End-to-end Feature representation compensation Regional pale-shaped self-attention

来源：评论

学校读者我要写书评

暂无评论

YOLO-UP: A High-Throughput pest detection Model for Dense Cotton Crops Utilizing UAV-Captured Visible Light Imagery

引用

IEEE ACCESS 2025年 13卷 19937-19945页

作者： Sun, Chenglei Bin Azman, Afizan Wang, Zaiyun Gao, Xiaoxiao Ding, Kai Taylors Univ Sch Comp Sci Subang Jaya 47500 Selangor Malaysia Shandong Vocat Coll Informat Technol Dept Elect & Commun Weifang 261061 Shandong Peoples R China Shandong Vocat Anim Sci & Vet Coll Dept Anim Sci & Technol Weifang 261061 Shandong Peoples R China Shandong Vocat Coll Informat Technol Dept Digital & Media Weifang 261061 Shandong Peoples R China

Accurate detection of pest species in cotton fields is vital for effective agricultural management and the development of pest-resistant crops. However, achieving high-throughput and precise pest detection in cotton fields remains a challenging task. Although unmanned aerial vehicle (UAV) enable the rapid acquisition of extensive crop images, detecting pests accurately from these images is difficult due to the small size of pests and background interference. This study introduces YOLO-pest, a novel pest detection model based on YOLOv8n, utilizing a personal cotton field imagery dataset acquired by UAVs. YOLO-pest incorporates a custom-designed SC3 module to enhance low-level feature extraction and employs the GeLU activation function to address the vanishing gradient issue. Additionally, the model optimizes the neck design to re-duce semantic discrepancies between feature layers, improving small-target detection, and integrates large-kernel separable convolutions to bolster high-level feature processing. Experimental results demonstrate that YOLO-pest outperforms original YOLOv8n models, with a 3.46 percentage points increase in mAP50, a 5.16 percentage points increase in Precision, and a 7.81 percentage points increase in Recall. YOLO-pest also shows superior Precision compared to DenseNet and FasterNet, with improvements of 1.14 and 6.13 percentage points, respectively. Overall, YOLO-pest offers high accuracy and a compact parameter footprint, making it highly effective for pest detection in UAV-acquired crop images.

关键词： Feature extraction Kernel Autonomous aerial vehicles Cotton YOLO Neck Crops Accuracy Sun Image edge detection UAV YOLOv8 pest detection cotton small target

来源：评论

学校读者我要写书评

暂无评论

pest-YOLO: A YOLOv5-Based Lightweight Crop pest detection Algorithm

引用

INTERNATIONAL JOURNAL OF ENGINEERING AND TECHNOLOGY INNOVATION 2025年第1期15卷 11-25页

作者： Luo, Wanbo Leshan Vocat & Tech Coll Dept Artificial Intelligence Leshan Peoples R China

Traditional crop pest detection methods face the challenge of numerous parameters and computations, making it difficult to deploy on embedded devices with limited resources. Consequently, a lightweight network is an effective solution to this issue. Based on you only look once (YOLO)v5, this paper aims to design and validate a lightweight and effective pest detector called pest-YOLO. First, a random background augmentation method is proposed to reduce the prediction error rate. Furthermore, a MobileNetV3-light backbone replaces the YOLOv5n backbone to reduce parameters and computations. Finally, the Convolutional Block Attention Module (CBAM) is integrated into the new network to compensate for the reduction in accuracy. Compared to the YOLOv5n model, the pest-YOLO model's Parameters and Giga Floating Point Operations (GFLOPs) decrease by about 33% and 52.5% significantly, and the Frames per Second (FPS) increase by approximately 11.1%. In contrast, the Mean Average Precision (mAP50) slightly declines by 2.4%, from 92.7% to 90.3%.

关键词： pest detection YOLOv5n MobileNetV3 CBAM

来源：评论

学校读者我要写书评

暂无评论

Apnet: Lightweight network for apricot tree disease and pest detection in real-world complex backgrounds

引用

PLANT METHODS 2025年第1期21卷 1-18页

作者： Li, Minglang Tao, Zhiyong Yan, Wentao Lin, Sen Feng, Kaihao Zhang, Zeyi Jing, Yurong Liaoning Tech Univ Sch Elect & Informat Engn Huludao 125105 Peoples R China Chinese Acad Agr Sci Res Inst Pomol Xingcheng 125100 Peoples R China Shenyang Ligong Univ Sch Automat & Elect Engn Shenyang 110159 Peoples R China

Apricot trees, serving as critical agricultural resources, hold a significant role within the agricultural domain. Conventional methods for detecting pests and diseases in these trees are notably labor-intensive. Many conditions affecting apricot trees manifest distinct visual symptoms that are ideally suited for precise identification and classification via deep learning techniques. Despite this, the academic realm currently lacks extensive, realistic datasets and deep learning strategies specifically crafted for apricot trees. This study introduces ATZD01, a publicly accessible dataset encompassing 11 categories of apricot tree pests and diseases, meticulously compiled under genuine field conditions. Furthermore, we introduce an innovative detection algorithm founded on convolutional neural networks, specifically devised for the management of apricot tree pests and diseases. To enhance the accuracy of detection, we have developed a novel object detection framework, APNet, alongside a dedicated module, the Adaptive Thresholding Algorithm (ATA), tailored for the detection of apricot tree afflictions. Experimental evaluations reveal that our proposed algorithm attains an accuracy rate of 87.1% on ATZD01, surpassing the performance of all other leading algorithms tested, thereby affirming the effectiveness of our dataset and model. The code and dataset will be made available at https://***/meanlang/ATZD01.

关键词： Disease detection pest detection Forest ecosystems Deep learning Agriculture image analysis

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Convolutional Neural Networks in a Farm pest detection Using Transfer Learning 5th

IoT-Based Convolutional Neural Networks in a Farm Pest Detec...

引用

5th International Conference on Computing Science, Communication and Security

作者： Jani, Keyurbhai A. Chaubey, Nirbhay Kumar Panchal, Esan Tripathi, Pramod Yagnik, Shruti Gujarat Technol Univ Comp IT Engn Ahmadabad 382424 Gujarat India Ganpat Univ Comp Sci Mahesana 384012 Gujarat India Govt Polytech Informat Technol Gandhinagar 382027 Gujarat India Indus Univ Comp Engn Ahmadabad 382115 Gujarat India

ISBN: (纸本)9783031751691;9783031751707

In this study explores agriculture pest detection using transfer learning with IoT devices, evaluating VGG16, VGG19, Inception, and Xception CNN architectures with the agripest dataset. VGG16 and VGG19 show effective learning with consistent accuracy improvements. Inception V3 exhibits strong training but with variability in validation metrics, while Xception demonstrates robust performance and strong generalization to new data. The integrated system utilizes cameras, sensors, and drones for real-time image processing through a gateway and cloud server with a customized agripest dataset. Transfer learning generates a deployable.h5 file for pest identification. The generated custom model deployed on a gateway or server to classifies pests, alerting farmers through SMS, dashboard, or mobile app notifications. This synergy between machine learning and IoT offers rapid and precise pest detection in agriculture.

关键词： IoT deep learning CNN pest detection cloud farm gateway

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Lenet, Resnet, and InceptionV3 Models for pest detection in Agriculture 1

Comparative Analysis of Lenet, Resnet, and InceptionV3 Model...

引用

1st International Conference on AIML-Applications for Engineering and Technology, ICAET 2025

作者： Mallela, Rajya Lakshmi Kamepalli, Sujatha Guttula, Sri Naga Sandhya Mendu, Sravanthi Pechetti, Bharath Raj Mendu, Monika Parvathi School of Computing Vignans Foundation for Science Technology and Research Guntur India

ISBN: (纸本)9798350355611

The detection of pests in agricultural fields is essential for advancing smart agriculture, aiding in optimizing resource management and enhancing crop yields. This study conducts a thorough performance assessment of three leadingedge deep learning architectures Lenet, Resnet, and InceptionV3specifically tailored for pest detection tasks. Utilizing a meticulously curated dataset consisting of annotated images of crops affected by various pests, each model was trained and evaluated under identical conditions to ensure a fair comparison. Each model's performance was thoroughly assessed using several key metrics, including accuracy, precision, recall, and F1-score, to determine their efficiency in accurately identifying and categorizing pest infestations. The comparative analysis highlights the unique strengths and limitations of each architecture, offering a comprehensive understanding of their capabilities and limitations in real-world agricultural applications. The findings from this study provide critical insights into the applicability of Lenet, Resnet, and InceptionV3models in developing robust pest detection systems. By highlighting the most effective deep learning model for this purpose, the research contributes to ongoing efforts to enhance pest management strategies, thereby supporting sustainable agricultural practices. The results underscore the importance of selecting the appropriate deep-learning architecture to improve the performance and efficiency of automated pest detection, ultimately fostering smarter, more resilient agricultural systems. © 2025 IEEE.

关键词： Deep Learning Inception V3 Lenet pest detection Resnet

来源：评论

学校读者我要写书评

暂无评论

Double Self-Attention Based Fully Connected Feature Pyramid Network for Field Crop pest detection

引用

Computers, Materials and Continua 2025年第3期83卷 4353-4371页

作者： Zijun Gao Zheyi Li Chunqi Zhang Ying Wang Jingwen Su School of Information Science and Engineering Dalian Polytechnic University Dalian 116034 China

pest detection techniques are helpful in reducing the frequency and scale of pest outbreaks; however, their application in the actual agricultural production process is still challenging owing to the problems of inter-species similarity, multi-scale, and background complexity of pests. To address these problems, this study proposes an FD-YOLO pest target detection model. The FD-YOLO model uses a Fully Connected Feature Pyramid Network (FC-FPN) instead of a PANet in the neck, which can adaptively fuse multi-scale information so that the model can retain small-scale target features in the deep layer, enhance large-scale target features in the shallow layer, and enhance the multiplexing of effective features. A dual self-attention module (DSA) is then embedded in the C3 module of the neck, which captures the dependencies between the information in both spatial and channel dimensions, effectively enhancing global features. We selected 16 types of pests that widely damage field crops in the IP102 pest dataset, which were used as our dataset after data supplementation and enhancement. The experimental results showed that FD-YOLO’s [email protected] improved by 6.8% compared to YOLOv5, reaching 82.6% and 19.1%–5% better than other state-of-the-art models. This method provides an effective new approach for detecting similar or multiscale pests in field crops.

关键词： pest detection YOLOv5 feature pyramid network transformer attention module

来源：评论

学校读者我要写书评

暂无评论

pest detection in Agricultural Farms using SqueezeNet and Multi-Layer Perceptron Model

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第6期15卷 802-808页

作者： Yulita, Intan Nurma Prabuwono, Anton Satria Ardiansyah, Firman Rejito, Juli Sholahuddin, Asep Rosadi, Rudi Univ Padjadjaran Dept Comp Sci Sumedang Indonesia King Abdulaziz Univ Fac Comp & Informat Technol Rabigh Rabigh Saudi Arabia Inst Teknol Bisnis Ahmad Dahlan Lamongan Management Bandung Indonesia

Pes detection is essential to protect agricultural systems from economic losses, lower food production, and environmental degradation. detection of pests is a crucial aspect of agricultural sustainability because it helps to allocate resources, reduce production costs, and increase producers' profits. Artificial intelligence (AI) has revolutionized the detection of agronomic pests by employing deep learning models to accurately detect individual pests and differentiate between species and life stages. Combining SeueezeNet and Multi-Layer Perceptron, this study extracts feature vectors from image data to detect pests. There are four primary phases: preprocessing, image embedding with SqueezeNet, the final classifier with MLP, and 10-fold crossvalidation. Data for this study is acquired in the form of plant pests. The total number of images acquired is 3150, with 350 from each class. Based on the research, the combination model demonstrates excellent performance. Each experiment's accuracy is greater than 99 %. It shows that Squeezenet can effectively extract the data's features, whereas Multi-Layer Perceptron can process these features for optimal classification performance. Even though there are still several classes, such as mites, sawflies, and stem borer, that have not been correctly classified. Since each image's background is unique, it cannot be classified correctly. These promising findings have broad implications for boosting agricultural output and decreasing pest-related losses. Optimal use of this approach in a variety of agricultural contexts requires more study and field testing.

关键词： pest detection Squeezenet multi-layer perceptron deep learning

来源：评论

学校读者我要写书评

暂无评论

pest detection using Adaptive Thresholding

Pest Detection using Adaptive Thresholding

引用

IEEE International Conference on Computing, Communication and Automation (ICCCA)

作者： Kumar, Yogesh Dubey, Ashwani Kumar Jothi, Adityan Amity Univ Amity Sch Engn Noida India

ISBN: (纸本)9781509064717

pest detection is crucial to secure crops and ensure food quality. A lot of work is being carried out for the effective identification of pests. In this paper we will develop a novel and fast methodology to detect and enumerate the pests present in an image using rapid feature detection algorithm. The amount of pesticides being used for agriculture pollutes the environment, with sophisticated machine vision systems that implement this algorithm we can make machines that utilize pesticides effectively by selective targeting pests using image processing. In the current scenario, human labor is used for the manual detection of pests which is not highly accurate. Automation is required in this field as it would be accurate in the detection of pests in crops. This paper proposes a system that would automate the detection of pests in crops using digital image processing techniques.

关键词： pest detection image processing image segmentation median filtering image denoising adaptive thresholding

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：